No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Compact Correlated Features for Writer Independent Signature Verification
Abstract
This paper considers the offline signature verification problem which is considered to be an important research line in the field of pattern recognition. In this work we propose hybrid features that consider the local features and their global statistics in the signature image. This has been done by creating a vocabulary of histogram of oriented gradients (HOGs). We impose weights on these local features based on the height information of water reservoirs obtained from the signature. Spatial information between local features are thought to play a vital role in considering the geometry of the signatures which distinguishes the originals from the forged ones. Nevertheless, learning a condensed set of higher order neighbouring features based on visual words, e.g., doublets and triplets, continues to be a challenging problem as possible combinations of visual words grow exponentially. To avoid this explosion of size, we create a code of local pairwise features which are represented as joint descriptors. Local features are paired based on the edges of a graph representation built upon the Delaunay triangulation. We reveal the advantage of combining both type of visual codebooks (order one and pairwise) for signature verification task. This is validated through an encouraging result on two benchmark datasets viz. CEDAR and GPDS300.
... The best recognition rate of 99.40% has been attained using the MCYT-100 dataset. The proposed approach attained recognition accuracy of 96.87% using the GPDS-300 dataset, which surpassed the stateof-the-art approaches (Dutta et al. 2016;Dey et al. 2017;Hadjadjiet al. 2017). Whereas on the GPDS-960 dataset, they attained 97.19% accuracy which is superior to existing approaches (Dutta et al. 2016;Dey et al. 2017;Bouamraet al. 2018). ...
... The proposed approach attained recognition accuracy of 96.87% using the GPDS-300 dataset, which surpassed the stateof-the-art approaches (Dutta et al. 2016;Dey et al. 2017;Hadjadjiet al. 2017). Whereas on the GPDS-960 dataset, they attained 97.19% accuracy which is superior to existing approaches (Dutta et al. 2016;Dey et al. 2017;Bouamraet al. 2018). OnBHSig260 Hindi and BHSig260 Bengali, the proposed approach attained recognition rates of 97.12% and 98.40%, respectively which are better as compared to existing approaches (Dutta et al. 2016;Pal et al. 2016;Dey et al. 2017). ...
... Whereas on the GPDS-960 dataset, they attained 97.19% accuracy which is superior to existing approaches (Dutta et al. 2016;Dey et al. 2017;Bouamraet al. 2018). OnBHSig260 Hindi and BHSig260 Bengali, the proposed approach attained recognition rates of 97.12% and 98.40%, respectively which are better as compared to existing approaches (Dutta et al. 2016;Pal et al. 2016;Dey et al. 2017). In terms of comparison with other state-of-the-art approaches, they also considered EER. ...
Signature identification and verification are some of the biometric systems used for personal identification. Signatures can be considered as authentication of an individual by the analysis of handwriting style, subjected to inter-personal and intra-personal variations. This paper presents an extensive systematic overview of online and offline signature identification and verification techniques. In offline signature verification, surveys related to two approaches, namely, writer-dependent, and writer-independent approaches are presented. Moreover, the compiled study of feature extraction and classification techniques used for signature identification and verification process has also been incorporated. Several databases introduced in the literature are considered to evaluate different signature identification and verification techniques and corresponding results are reported in this article. The entire survey is further summarized in the form of a table for comparisons. In order to reveal the superiority of the present survey, the comparison of the present survey with the existing recent survey works has also been presented. Finally, future directions are provided for further research.
... Although many offline signature verification schemes have been proposed [7][8][9][10][11][12][13][14][15]; mostly the schemes are either purely handcrafted feature based or conventional machine learning based. Because of very less textural information in the images, handcrafted features do not help much and feature engineering becomes vital [6]. ...
... It is clear from the table that our method gives comparative results on the publicly available datasets with the state of the art methods [7,[11][12][13]28]. Inverse Discriminative Networks (IDN) [11] uses four parallel streams from two samples. ...
... -123 performance of their system is degraded. With our model we have achieved accuracy of 87.5% on GPDS dataset, which is slightly lower than the previously reported method [12], but it should be noted that we have reported results with the fivefold cross validation. Our method gives higher accuracy on Hindi and Bengali datasets that is, 95.7% and 96.5%, respectively. ...
Signature biometrics is a widely accepted and used modality to verify the identity of an individual in many legal and financial organisations. A writer and language‐independent signature identification method that can distinguish between the genuine and forged sample irrespective of the language of the signature has been proposed. To extract the distinguishing features, a pre‐trained model GoogLeNet, which is fine‐tuned with the largest signature dataset present till date (GPDS Synthetic), has been used. The proposed method is tested over the BHSig260 (contains images from two regional languages, Bengali and Hindi) dataset. With the help of the above fine‐tuned model, knowledge is transferred to the publicly available datasets–BHSig260 and MCYT‐75. The features extracted using the fine‐tuned model has been fed to the support vector machine (SVM) classifiers. With the proposed method, 96.5% and 95.7% accuracy on Bengali and Hindi datasets, and 93% on MCYT‐75 with skilled forged samples have been achieved respectively.
... We use 100 people's signatures to train our model and the rest 60 persons' signatures as testing data. On these two datasets, we compare our method with approaches such as SigNet (Dey et al. 2017), FHTF (Bhunia, Alaei, and Roy 2019), Correlated Feature (Dutta, Pal, and Lladós 2016) and others. Table 2 shows the comparison results. ...
... GPDS Synthetic Dataset (Ferrer, Diaz-Cabrera, and Morales 2015b) is a large-scale and challenging signature (Dutta, Pal, and Lladós 2016). Table 3 shows the experiment results. ...
Offline signature verification is a challenging issue that is widely used in various fields. Previous approaches model this task as a static feature matching or distance metric problem of two images. In this paper, we propose a novel Static-Dynamic Interaction Network (SDINet) model which introduces sequential representation into static signature images. A static signature image is converted to sequences by assuming pseudo dynamic processes in the static image. A static representation extracting deep features from signature images describes the global information of signatures. A dynamic representation extracting sequential features with LSTM networks characterizes the local information of signatures. A dynamic-to-static attention is learned from the sequences to refine the static features. Through the static-to-dynamic conversion and the dynamic-to-static attention, the static representation and dynamic representation are unified into a compact framework. The proposed method was evaluated on four popular datasets of different languages. The extensive experimental results manifest the strength of our model.
... These works are either holistic or component level approach. Well known global features like signature window size, projection profile, signature contour, energy [4], centroid and geometric information [5], statistical texture information [6], quad tree based structural information [7], SURF [8], SIFT [9] like global descriptor, wavelet based features [10], grid and geometry based information [11], fuzzy modeling based feature fusion [12], HOG [13] were used for various signature recognition task on non-Indic scripts. Among the popular works on Indic scripts gradient and Zernike moments [14], contour information based on chain code [15], LBP [16] were considered. ...
... Comparison with Handcrafted Features. We compare the performance of the proposed architecture with some well-known state-of-the-art texture based handcrafted features namely: Gray level co-occurrence matrix (GLCM) [20], Zernike moments [21], Histogram of oriented gradient (HOG) [13], Local binary pattern (LBP) [20], Weber local descriptor (WLD) [22] and Gabor Wavelet Transform (GWT) [30]. For GLCM, 22 dimensional feature vectors were generated applying different statistical properties and it produced a writer identification accuracy of 62.10% for Roman and 72.73% for Devanagari scripts, respectively. ...
Automated approach for human identification based on biometric traits has become popular research topic among the scientists since last few decades. Among the several biometric modalities, handwritten signature is one of the very common and most prevalent approaches. In the past, researchers have proposed different handcrafted feature-based techniques for automatic writer identification from offline signatures. Currently huge interests towards deep learning-based solutions for several real-life pattern recognition problems have been found which revealed promising results. In this paper, we propose a light-weight CNN architecture to identify writers from offline signatures written by two popular scripts namely Devanagari and Roman. Experiments were conducted using two different frameworks which are as follows: (i) In first case, signature script separation has been carried out followed by script-wise writer identification, (ii) Secondly, signature of two scripts was mixed together with various ratios and writer identification has been performed in a script independent manner. Outcome of both the frameworks have been analyzed to get the comparative idea. Furthermore, comparative analysis was done with recognized CNN architectures as well as handcrafted feature-based approaches and the proposed method shows better outcome. The dataset used in this paper can be freely downloaded from the link: https://ieee-dataport.org/open-access/multi-script-handwritten-signature-roman-devanagari for research purpose.
... There has been lot of work present in the literature [2, 6, 8, 13, 16-19, 23-26, 28, 32, 35, 38-41, 44-46]. The signature verification methods has been divided in three categories based on the classifier used, i.e., distance-based [19,38,41,42], SVM-based [8,39,46] and neural networkbased [2,4,25,36]. ...
... The resultant feature set has been given to the SVM for verification purpose. In [8], the authors have proposed a method that was based on hybrid HOG features. Global statistics and key points have been extracted using the HOG features from the input signature image. ...
Signature verification has been one of the major researched areas in the field of computer vision. Many financial and legal organizations use signature verification as access control and authentication. Signature images are not rich in texture; however, they have much vital geometrical information. Through this work, we have proposed a signature verification methodology that is simple yet effective. The technique presented in this paper harnesses the geometrical features of a signature image like center, isolated points, connected components, etc., and with the power of Artificial Neural Network (ANN) classifier, classifies the signature image based on their geometrical features. Publicly available dataset MCYT, BHSig260 (contains the image of two regional languages Bengali and Hindi) has been used in this paper to test the effectiveness of the proposed method. We have received a lower Equal Error Rate (EER) on MCYT 100 dataset and higher accuracy on the BHSig260 dataset.
... In [223], a multifeatured extra tion method was proposed that allows one to extract a range of global to very local features by varying the scale of a virtual grid used to partition each signature image. The signature can also be described by a quad-tree structure and an artificial immune recognition (AIR) system for verification [232] or through interest points such as SIFT [45], SURF [163], BRISK [61], KAZE [184], or FREAK [159]. Additionally, fuzzy membership functions are still used in signature verification. ...
Handwritten signatures are biometric traits at the center of debate in the scientific community. Over the last 40 years, the interest in signature studies has grown steadily, having as its main reference the application of automatic signature verification, as previously published reviews in 1989, 2000, and 2008 bear witness. Ever since, and over the last 10 years, the application of handwritten signature technology has strongly evolved, and much research has focused on the possibility of applying systems based on handwritten signature analysis and processing to a multitude of new fields. After several years of haphazard growth of this research area, it is time to assess its current developments for their applicability in order to draw a structured way forward. This perspective reports a systematic review of the last 10 years of the literature on handwritten signatures with respect to the new scenario, focusing on the most promising domains of research and trying to elicit possible future research directions in this subject.
... The table provides the accuracy, false acceptance rate (FAR), false rejection rate (FRR), and equal error rate (EER) for each method. Compact correlated features[32]: This method achieved an accuracy of 88.79%. The FAR, FRR, and EER were all 11.21%. ...
The verification of handwritten signatures is integral to numerous applications such as authentication and document verification. The efficacy of an offline signature verification system relies heavily on the feature extraction stage, because it significantly affects the performance of the system. Both the quality and quantity of extracted features play pivotal roles in enabling the system to distinguish between genuine and forged signatures. In this study, we introduce a novel approach aimed at optimizing the hyperparameters of a Convolutional Neural Network (CNN) model for handwritten signature verification by leveraging a Particle Swarm Optimization (PSO) algorithm. The PSO algorithm, inspired by the flocking behavior of birds, is a population-based optimization method. We delineated a search space encompassing various hyperparameter ranges, including the number of convolutional filters, dense layers, dropout rate, and learning rate. Through iterative updates to the positions and velocities of the particles, the PSO algorithm navigates this search space to identify the optimal set of hyperparameters that maximizes the accuracy of the CNN model. Our approach was evaluated across diverse datasets including BHSig260-Bengali, BHSig260-Hindi, GPDS, and CEDAR, each containing a varied assortment of handwritten signature images. The experimental results demonstrate the effectiveness of our proposed method, achieving a remarkable accuracy of 98.3% on the testing dataset.
... Drouhard et al. [10] utilized the directional probability density function as a global characteristic to describe the signature. A. Dutta et al. [40] proposed a method for offline signature verification. Their approach combines local features and global statistics within signature images using histogram of oriented gradients (HOGs). ...
In the area of biometrics and document forensics, handwritten signatures are one of the most commonly accepted symbols. Thus, financial and commercial institutions usually use them to verify the identity of an individual. However, offline signature verification is still a challenging task due to the difficulties in discriminating the minute but significant details between genuine and skilled forged signatures. To tackle this issue, we propose a novel writer-independent offline signature verification approach using attention-based multiple siamese networks with primary representation guiding. The proposed multiple siamese networks regard the reference signature images, query signature images, and their corresponding inverse images as inputs. These images are fed to four weight-shared parallel branches, respectively. We present an efficient and reliable mutual attention module to discover prominent stroke information from both original and inverse branches. In each branch, feature maps of the first convolution are utilized to guide the combination with deeper features, named as primary representation guiding, which guides the model into concerning the shallow stroke information. The four branches are concatenated in an ordered way and are put into four contrastive pairs, which is helpful to obtain useful representations by comparing reference and query samples. Four contrastive pairs generate four preliminary decisions independently. Then, the eventual verification result is created based on the four preliminary decisions using a voting mechanism. In order to assess the performance of the proposed method, extensive experiments on four widely used public datasets are conducted. The experimental results demonstrate that the proposed method outperforms existing approaches in most cases and can be applied to various language scenarios.
... Signature forgery is the fraudulent copying of another person's signature for a particular purpose. Due to every person's different nature and personality, every signature has a different pattern and shape, but human senses have limitations in the verification process if the patterns compared are very similar [7], [8]. This condition can result in a missverified signature strikingly similar to the genuine one. ...
Signature genuine verifications of offline hand-written signatures are critical for preventing forgery and fraud. With the growth of protecting personal identity and preventing fraud, the demand for an automatic system for signature verification is high. The signature verification system is then studied by many researchers using various methods, especially deep learning-based methods. Hence, deep learning has a problem. Deep learning requires much training time for the data to obtain the best model accuracy result. Therefore, this paper proposed a CNN Batch Normalization, the CNN architectural adaptation model with a normalization batch number added, to obtain a CNN model optimization with high accuracy and less training time for offline hand-written signature verification. We compare CNN with our proposed model in the experiments. The research method in this study is data collection, pre-processing, and testing using our private signature dataset (collected by capturing signature images using a smartphone), which becomes the difficulties of our study because of the different lighting, media, and pen used to sign. Experiment results show that our model ranks first, with a training accuracy of 88.89%, an accuracy validation of 75.93%, and a testing accuracy of 84.84%—also, the result of 2638.63 s for the training time consumed with CPU usage. The model evaluation results show that our model has a smaller EER value; 2.583, with FAR = 0.333 and FRR = 4.833. Although the results of our proposed model are better than basic CNN, it is still low and overfitted. It has to be enhanced by better pre-processing steps using another augmentation method required to improve dataset quality.
... Some local or global feature vectors were computed for classification in both cases. Some of the common global features are signature contour, window size, energy [3], statistical texture patterns [4],information based on quad-tree decomposition [5], the center of gravity and geometric information [6], and global feature descriptors namely SURF [7], SIFT [8], HOG [9], wavelet decomposition [10], feature fusion based on fuzzy modeling [11], considered for signature-based writer identification from non-Indic scripts. Among the well-known works on Indic scripts, moment-based features [12], chain code contour information [13], and local binary patterns [14] are also considered. ...
... First, the user's signature was compared to a sample signature kept in the database using PMT (pixel matching technique). In 2016, Assia Hamadene et al. [16] suggested a one-class WI (writer-independent) approach with fewer references and feature distinction methods using a threshold for classification. The contourlet transform-based directional code co-occurrence matrix feature creation method is used in the suggested system [17]. ...
One of the toughest biometrics and document forensics problems is confirming a signature's authenticity and legal identity. A forgery may vary from a genuine signature by specific distortions. Therefore, it is necessary to continuously monitor crucial distinctions between real and forged signatures for secure work and economic growth, but this is particularly difficult in writer-independent tasks. We thus propose an innovative and sustainable writer-independent approach based on a Siamese neural network for offline signature verification. The Siamese network is a twin-like structure with shared weights and parameters. Similar and dissimilar images are exposed to this network, and the Euclidean distances between them are calculated. The distance is reduced for identical signatures, and the distance is increased for different signatures. Three datasets, namely GPDS, BHsig260 Hindi, and BHsig260 Bengali datasets, were tested in this work. The proposed model was analyzed by comparing the results of different parameters such as optimizers, batch size, and the number of epochs on all three datasets. The proposed Siamese neural network outperforms the GPDS synthetic dataset in the English language, with an accuracy of 92%. It also performs well for the Hindi and Bengali datasets while considering skilled forgeries.
... Up to now, many methods have been proposed for offline handwritten signature verification [19][20][21]. Many studies often use texture features extraction such as gray-level co-occurrence matrix [22] and Local Binary Patterns [23]; directional-based features such as directional-pdf [24] and histogram of oriented gradients [25]; feature extractors specifically designed for offline handwritten signatures, such as the estimation of strokes by fitting Bezier curves [26]. Moreover, an inverse discriminative network [27] is proposed for writerindependent handwritten signature verification. ...
Offline handwritten signature verification is one of the most prevalent and prominent biometric methods in many application fields. Siamese neural network, which can extract and compare the writers’ style features, proves to be efficient in verifying the offline signature. However, the traditional Siamese neural network fails to represent the writers’ writing style fully and suffers from low performance when the distribution of positive and negative handwritten signature samples is unbalanced. To address this issue, this study proposes a two-stage Siamese neural network model for accurate offline handwritten signature verification with two main ideas: (a) adopting a two-stage Siamese neural network to verify original and enhanced handwritten signatures simultaneously, and (b) utilizing the Focal Loss to deal with the extreme imbalance between positive and negative offline signatures. Experimental results on four challenging handwritten signature datasets with different languages demonstrate that compared with state-of-the-art models, our proposed model achieves better performance. Furthermore, this study tries to extend the proposed model to the Chinese signature dataset in the real environment, which is a significant attempt in the field of Chinese signature identification.
... Moreover, texture descriptors and interest key-points detection techniques (e.g. SIFT, SURF, BRISK, KAZE, FREAK) are frequently used in OSV to generate vectored representations (Dutta et al., 2016;Hu & Chen, 2013;Malik et al., 2014Malik et al., , 2013Manabu Okawa, 2018b;Ruiz-del-Solar et al., 2008;Y. Serdouk et al., 2014;Vargas et al., 2011;Yilmaz et al., 2011). ...
Handwritten signature is a common biometric trait, widely used for confirming the presence or the consent of a person. Offline Signature Verification (OSV) is the task of verifying the signer using static signature images captured after the finish of signing process, with many applications especially in the domain of forensics. Deep Convolutional Neural Networks (CNNs) can generate efficient feature representations, but their training is data-intensive. Since limited training data is an intrinsic problem of an OSV system’s development, this work focuses on addressing the problem of learning informative features by employing prior knowledge from a similar task in a domain with an abundance of training data. In particular, we demonstrate that an appropriate pre-training of a CNN model in the task of handwritten text-based writer identification task, can dramatically improve the efficiency of the CNN in the OSV task, enabling to obtain state-of-the-art performance with an order of magnitude less training signature samples. In the proposed scheme, after the pre-training of the CNN in writer identification task through specially processed handwritten text data, the learned features are tailored to the signature problem though a metric learning stage that utilizes contrastive loss to learn a mapping of the signatures’ features to a latent space that suits the OSV task. At the final stage, the proposed scheme utilizes Writer-Dependent (WD) classifiers learned on a few reference samples from each writer. Our system is tested on the three challenging signature datasets, CEDAR, MCYT-75 and GPDS300GRAY. The obtained accuracy in terms of Equal Error Rates (EER) is statistically equivalent to the popular SigNet CNN, despite a significantly smaller training set of signature images and no use of skilled forgeries signatures during training.
... Moreover, texture descriptors and interest key-points detection techniques (e.g. SIFT, SURF, BRISK, KAZE, FREAK) are frequently used in OSV to generate vectored representations (Dutta et al., 2016;Hu & Chen, 2013;Malik et al., 2014Malik et al., , 2013Manabu Okawa, 2018b;Ruiz-del-Solar et al., 2008;Y. Serdouk et al., 2014;Vargas et al., 2011;Yilmaz et al., 2011). ...
... The Deep Neural Network (DNN) extensively used to solve the signature recognition and also segmentation task [11]. Hybrid Local and global features are used for identify the genuine signature form forded signature [12,13]. Eigen value technique applied for signature verification system [14]. ...
As the technology improves, there are many new innovations which give the security frameworks with different methods that are used to identify a person. Signature recognition is one of methods used to identify person. In this paper, offline signature recognition using back propagation neuron network system and image processing techniques has been proposed. Preprocessing of signature can be done using image processing techniques which involves RGB2Gray conversion, filtering, adjusting, thresholding followed by canny edge detection and at the last image scaling applied to reduce the processing time. Processed image feature is extracted using back propagation neuron network system with defined number of neurons and hidden layers. Similarly, data set images undergo preprocessing operation and features are extracted. Based on number of layers that are hidden and neuron, better recognition rate is obtained. The proposed method shows that the experimental result has more success rate.
In hyperspectral image (HSI) classification scenarios, deep learning-based methods have achieved excellent classification performance, but often rely on large-scale training datasets to ensure accuracy. However, in practical applications, the acquisition of hyperspectral labeled samples is time consuming, labor intensive and costly, which leads to a scarcity of obtained labeled samples. Suffering from insufficient training samples, few-shot sample conditions limit model training and ultimately affect HSI classification performance. To solve the above issues, an active learning (AL)-based multipath residual involution Siamese network for few-shot HSI classification (AL-MRIS) is proposed. First, an AL-based Siamese network framework is constructed. The Siamese network, which has relatively low demand for sample data, is adopted for classification, and the AL strategy is integrated to select more representative samples to improve the model’s discriminative ability and reduce the costs of labeling samples in practice. Then, the multipath residual involution (MRIN) module is designed for the Siamese subnetwork to obtain the comprehensive features of the HSI. The involution operation was used to capture the fine-grained features and effectively aggregate the contextual semantic information of the HSI through dynamic weights. The MRIN module comprehensively considers the local features, dynamic features and global features through multipath residual connections, which improves the representation ability of HSIs. Moreover, a cosine distance-based contrastive loss is proposed for the Siamese network. By utilizing the directional similarity of high-dimensional HSI data, the discriminability of the Siamese classification network is improved. A large number of experimental results show that the proposed AL-MRIS method can achieve excellent classification performance with few-shot training samples, and compared with several state-of-the-art classification methods, the AL-MRIS method obtains the highest classification accuracy.
With the recent advancements in deep learning techniques, the application areas of unstructured data analytics are emerging in multiple domains. One of the popular applications is analyzing image unstructured data. Multiple image analytics-based solutions have been developed to establish an autonomous, cutting-edge computer-based approach for identification and verification. The exponential growth in text documents, images, and videos in every domain is driving the development of multiple image analytics-based applications to get insights and improve solutions. Secure authentication and verification of handwritten signatures play an important role in security and authentication, particularly in financial institutions, legal transactions, etc. One of the exciting applications of Deep Learning is automated signature verification for person identifications. Since signature verification is the most commonly accepted biometric attribute by law enforcement officials and agencies, making it more secure is a major challenging task. In the proposed work, the author developed an efficient multi-dilation convolutional neural network-based model for handwritten signature verification. It has been observed that the proposed model is memory efficient and does not require many pre-processing and hardware resources like GPU. The proposed model is validated on the CEDAR dataset which contains 24 genuine and 24 forgery off-line signatures for each of 55 writers. The authors have made a comparative analysis of the proposed method with other state-of-the-art methods discussed in the literature. The model achieves more than 99% accuracy with an equal error rate of 6.00 which is a good improvement over the other existing methods.
Authenticating important documents by identifying individuals using handwritten signatures make signature verification a critical task. Interpersonal similarity and intrapersonal variation of individuals along with high skilled imitation of signature structure make automatic signature verification a challenging task. In such scenarios, a signature verification system should detect the small differences between genuine and forged signatures with high efficacy. This paper proposed a novel approach towards offline signature verification where a hybrid deep learning network, consisting of a Convolutional Neural Network and a Bidirectional Long Short Term Memory network is used. Signature written with freehand and an imitation of it are almost identical structurally. Deep Neural Network is used to recognize skilled forgery from genuine signatures because of its capability to learn critical details and subtle patterns from the image pixels. A Convolutional Neural Network is trained, and the trained network is then used to extract diverse features of the signature images. The generated feature vectors are then used for classification using Bidirectional Long Short Term Memory. The hybrid deep learning network classifies the input signature as skilled forgery or genuine with high accuracy. For this work, state-of-the-art datasets, such as, GPDS-300, GPDS-Bengali, GPDS-Devanagari, CEDAR, BHSig260-Bengali, BHSig260-Hindi, and a local dataset, Meitei Mayek signature are used. In order to verify the robustness of the system, different multi-scripted offline signatures belonging to multi-lingual Indian society, are used for evaluation. The experimental results determined from multi-scripted signatures, exhibit that the proposed system is found comparable to many state-of-the-art systems and in some specific cases, it out performs some of the existing systems.
In this paper problem of offline signature verification has been discussed with a novel high-performance convolution Siamese network. The paper proposes modifications in the already existing convolution Siamese network. The proposed method makes use of the Batch Normalization technique instead of Local Response Normalization to achieve better accuracy. The regularization factor has been added in the fully connected layers of the convolution neural network to deal with the problem of overfitting. Apart from this, a wide range of learning rates are provided during the training of the model and optimal one having the least validation loss is used. To evaluate the proposed changes and compare the results with the existing solution, our model is validated on three benchmarks datasets viz. CEDAR, BHSig260, and GPDS Synthetic Signature Corpus. The evaluation is done via two methods firstly by Test-Train validation and then by K-fold cross-validation (K = 5), to test the skill of our model. We show that the proposed modified Siamese network outperforms all the prior results for offline signature verification. One of the major advantages of our system is its capability of handling an unlimited number of new users which is the drawback of many research works done in the past.
In this work, we have proposed a multi-label classification algorithm for signature images that can be used to solve multiple objectives: i) It can tell the identity of the image. ii) Can interpret the language of the content written in the image. iii) It can also identify whether the given image is the genuine signature of the person or the forged one. This paper has used the pretrained model GoogLeNet, that has been finetuned on the largest signature dataset present (GPDS). GoogLeNet is used to extract the features from the signature images, and these features are fed to the three-layer neural network. The neural network has been used for the classification of the features of the image. The model has been trained or tested against two regional datasets Hindi and Bengali datasets.KeywordsSignatureBehavioralNeural networkClassification
Offline signature verification is one of the most challenging tasks in biometric authentication. Despite recent advances in this field using image recognition and deep learning, there are many remaining things to be explored. The most recent technique, which is Siamese convolutional neural network, has been used a lot in this field and has achieved great results. This paper presents an architecture that combines the power of Siamese Triplet CNN and a fully-connected neural network for binary classification to automatically verify genuine and forgery signatures even if the forged signature is highly skilled. On the challenging public dataset for signature verification BHSig260, the proposed model can achieve a low False Acceptance Rate = 13.66, which is slightly better than the reference model. Based on this approach, the one-shot learning should make it possible to determine if the input image is genuine or fraudulent just from one base image. Therefore, our model is expected to be extremely suitable for practical problems, such as banking systems or mobile authentication applications, in which the amount of data for each identity is limited in quantity and variety.
To further improve the accuracy of multilingual off-line handwritten signature verification, this paper studies the off-line handwritten signature verification of monolingual and multilingual mixture and proposes an improved verification network (IDN), which adopts user-independent (WI) handwritten signature verification, to determine the true signature or false signature. The IDN model contains four neural network streams with shared weights, of which two receiving the original signature images are the discriminative streams, and the other two streams are the reverse stream of the gray inversion image. The enhanced spatial attention models connect the discriminative streams and reverse flow to realize message propagation. The IDN model uses the channel attention mechanism (SE) and the improved spatial attention module (ESA) to propose the effective feature information of signature verification. Since there is no suitable multilingual signature data set, this paper collects two language data sets (Chinese and Uyghur), including 100,000 signatures of 200 people. Our method is tested on the self-built data set and the public data sets of Bengali (BHsig-B) and Hindi (BHsig-H). The method proposed in this paper has the highest discrimination rate of FRR of 10.5%, FAR of 2.06%, and ACC of 96.33% for the mixture of two languages.
Signature verification plays a significant role in many biometric authentication places. Many financial institutes require a robust signature verification process for check clearance, loan sanction, processing, pension relation documents, etc. Expert forgeries make it hard to authenticate an individual's identification based on signatures. Typically, this occurs when the forger understands the user's intricate features of the signature and strives to mimic it. Online signature verification approaches can extract various features such as keystrokes, pressure of the pointer, duration between the strokes and the lettering styles, so that verification becomes effective. However, the lack of these intricate details in offline signature, the authentication process becomes much more difficult. To address these issues, in this paper we propose deep learning-based approaches for offline signature verification. In this regard, we have used ZFNet, LeNet and AlexNet architectures with CEDAR, BHSig20 and UTsig datasets for our extensive. experimentation. We propose a learning model in which the dataset consists of multiple genuine and forged signatures. Further, performance analysis of these techniques has been carried out. It was found that LeNet has provided better training and testing accuracy with above 82% performance.
Writer independent offline signature verification is one of the most challenging tasks in pattern recognition as there is often a scarcity of training data. To handle such data scarcity problem, in this paper, we propose a novel self-supervised learning (SSL) framework for writer independent offline signature verification. To our knowledge, this is the first attempt to utilize self-supervised setting for the signature verification task. The objective of self-supervised representation learning from the signature images is achieved by minimizing the cross-covariance between two random variables belonging to different feature directions and ensuring a positive cross-covariance between the random variables denoting the same feature direction. This ensures that the features are decorrelated linearly and the redundant information is discarded. Through experimental results on different data sets, we obtained encouraging results.
Offline handwritten signatures play an important role in biometrics and document forensics, and it has been widely used in the fields of finance, judiciary and commerce. However, the skilled signature forgeries bring challenges and difficulties to personal privacy protection. Thus it is vital to discover micro but critical details between genuine signatures and corresponding skilled forgeries in signature verification tasks. In this paper, we propose an attention based Multiple Siamese Network (MSN) to extract discriminative information from offline handwritten signatures. MSN receives the reference and query signature images and their corresponding inverse images. The received images are fed to four parallel branches. We develop an effective attention module to transfer the information from original branches to inverse branches, which attempts to explore prominent features of handwriting. The weight-shared branches are concatenated in a particular way and formed into four contrastive pairs, which contribute to learn useful representations by comparisons of these branches. The preliminary decisions are generated from each contrastive pair independently. Then, the final verification result is voted from these preliminary decisions. In order to evaluate the effectiveness of proposed method, we conduct experiments on three publicly available signature datasets: CEDAR, BHSig-B and BHSig-H. The experimental results demonstrate the proposed method outperforms that of other previous approaches.
Among various biometric systems, an offline signature verification system has been widely used in all fields such as in banks, educational institutes, legal procedures and, a criminal investigation where authentication and verification are utmost required. Despite the popularity of the online signature verification system, its offline counterpart still has great importance in developing countries, especially in rural areas, where easy availability of smart devices along with fast internet connection is not available. In this work, we have developed a language invariant offline signature verification model which is almost equally applicable for both writer dependent and writer independent scenarios. At first, an offline signature is collected as an image, following which a corresponding signal is generated using singular value decomposition. Then four different kinds of features namely, statistical, shape-based, similarity-based, and frequency-based are extracted from the transformed signal of the signature image. Next, to reduce the feature dimension, we have designed a novel wrapper feature selection method based on Red Deer Algorithm, a recently proposed meta-heuristic method, to keep only the relevant features to be used during signature authentication and verification process. Finally, a confidence score from the Naïve Bayes classifier has been used to perform the authentication and verification process. Our model has been evaluated on CEDAR (English), UTSig (Persian), Sigcomp 2011 Dutch, Sigcomp 2011 Chinese, and SigWIcomp 2015 Bengali signature datasets. Obtained results confirm that the proposed model can outperform many of its predecessors.
Several researchers have worked on signature verification problems from different aspects utilizing insights from signal processing and computer vision, since the last few decades. Despite the advancement in technology, signature model building with an appropriate classifier to distinguish between skilled forgeries and genuine is still a critical problem. This paper presents Siamese neural network-based signature verification system which consists of twin convolutional neural networks with shared weights which maximize the distance between dissimilar pairs while simultaneously minimizing the distance between similar pairs. The signatures are paired among similar (genuine, genuine) and dissimilar (genuine, forged) pairs. This research achieves higher classification accuracy compared to state-of-the-art methods. The results are validated on our created dataset and CEDAR, UTSig, BHSig260, GDPS300, GDPS synthetic signature benchmark datasets.
KeywordsSignature verificationSiamese neural networkConvolutional neural networks
Handwritten signatures are a widespread biometric trait for person identification and verification. Reliable authentication and authorization of individuals are, however, challenging tasks due to possible skilled forgeries; especially when a forger has access to a given signature and deliberately tries to imitate it. This problem is even more emphasised in offline signature verification, where dynamic signature information is lost, resulting, as a consequence, in an increased difficulty discerning between genuine and forged signatures. To address this issue, solutions based on convolutional neural networks (CNN) are currently being devised to automatically extract features from a signature. Although highly performing, these methods require a high number of learnable parameters to produce meaningful signature representations, ultimately leading to long training times. In this paper, the R-SigNet architecture, a multi-task approach exploiting a relaxed loss to learn a reduced feature space for writer-independent (WI) signature verification, is presented. Compact generic features are automatically extracted by this network, so that a support vector machine (SVM) can be trained and tested in offline writer-dependent (WD) mode. By leveraging a small generic feature space, the proposed system achieves improved performances and reduced training times with respect to the current literature, as shown by the results obtained on several benchmark datasets.
Offline Signature verification is a biometric method with important applications in the financial, legal and administrative procedures. The verification process includes comparing the extracted features of a questioned signature with those of genuine signatures of a certain individual. There are many challenges in designing offline signature verification as the dynamic temporal features of the signature are not available. Deep Convolutional Neural Networks (DCNNs) have the great capability of extracting features from the signature images. Despite the important advantages of these networks, they are unable to recognize the spatial properties of each feature in the signature. In addition, max-pooling layers usually eliminate some features that are crucial for forgery detection. In this paper, we propose a novel signature verification model with a combination of a CNN and Capsule Neural Networks (CapsNet) in order to capture spatial properties of the signature features, improve the feature extraction phase, and reduce the complexity of the network. Moreover, we designed a new training mechanism in which a single network is trained simultaneously by two images at the same level so that the training parameters are reduced by half. Such mechanism does not require two separate networks for learning the features. Finally, a composite backbone architecture is presented with the hybrid of the proposed CNN-CapsNet models which we name CBCapsNet. The evaluation results demonstrate that our proposed model can improve accuracy and outperform prevalent signature verification methods in the community.
Information extraction is a fundamental task of many business intelligence services that entail massive document processing. Understanding a document page structure in terms of its layout provides contextual support which is helpful in the semantic interpretation of the document terms. In this paper, inspired by the progress of deep learning methodologies applied to the task of object recognition, we transfer these models to the specific case of document object detection, reformulating the traditional problem of document layout analysis. Moreover, we importantly contribute to prior arts by defining the task of instance segmentation on the document image domain. An instance segmentation paradigm is especially important in complex layouts whose contents should interact for the proper rendering of the page, i.e., the proper text wrapping around an image. Finally, we provide an extensive evaluation, both qualitative and quantitative, that demonstrates the superior performance of the proposed methodology over the current state of the art.
Handwritten signature verification is a widely used biometric for person identity authentication in document forensics. Despite the tremendous efforts in past research, offline signature verification still remains a challenge, particularly in discriminating between genuine signatures and skilled forgeries, because the difference of appearance between genuine and skilled forgery may be smaller than that between genuine ones. This challenge is even more critical in writer-independent scenario, where each writer has very few samples for training. This paper proposes a region based Deep Convolutional Siamese Network using metric learning method, which is applicable to both writer-dependent (WD) and writer-independent (WI) scenario. For representing minute but discriminative details, a Mutual Signature DenseNet (MSDN) is designed to extract features and learn the similarity measure from local regions instead of whole signature images. Based on local regions comparison, the similarity scores of multiple regions are fused for final decision of verification. In experiments on public datasets CEDAR and GPDS, the proposed method achieved state-of-the-art performance of 6.74% EER and 8.24% EER in WI scenario, respectively, and 1.67% EER and 1.65% EER in WD scenario, respectively.
Handwritten signature is one of the most popular biometric traits which have been addressed by researchers since the last few decades. Scientists have proposed disparate handcrafted feature-based techniques for signature verification in the past. Presently there has been an interest towards deep learning-based approaches which has demonstrated promising results across different avenues of pattern recognition problems. In this paper, light-weight CNN architecture named SigVer is proposed for Bangla offline writer independent signature verification. The proposed network was built with only six layers with no pooling in between convolution layers to minimize information loss. Experiments were performed on 2956 signatures from 57 writers and a highest accuracy of 99.49% was obtained. Further, comparative analysis was performed with established CNN architectures as well as handcrafted feature-based techniques and SigVer produced better results.
Offline signature verification remains the most commonly employed authentication modality and enjoys global acceptance. From the view point of computerized verification, concluding the authenticity of a signature offers a challenging problem for the pattern classification community. A major proportion of computerized solutions treat signature verification as a two-class classification problem where both genuine and forged signatures are employed for training purposes. For most of the real world scenarios however, only genuine signatures of individuals are available. This paper presents a signature verification technique that relies only on genuine signature samples. More precisely, we employ convolutional neural networks for learning effective feature representations and a one-class support vector machine that learns the genuine signature class for each individual. Experiments are carried out in a writer-dependent as well as writer-independent mode and low error rates are reported by only employing genuine signatures in the training sets.
Signature verification is one of the major field of biometrics for authentication of human beings. Biometrics refers to the metrics related to human characteristics. From the last decade, the research on signature verification is going vigorously, but still, the research problem is being explored. Due to multiple challenges present in automated signature verification and identification, the study is open and inspiration for researchers. The major objective of the offline signature verification system is to discriminate between genuine(original) and forged signatures. There are many factors that make the processing of offline signature very complex. This paper describes what kind of approaches used in previous research attempts. In those attempts, some of the methodologies achieved a significant improvement. We will analyze how the problem is handled to improve the verification and identification task in the existing literature.
The objective of this investigation is to present an interval-symbolic representation based method for offline signature verification. In the feature extraction stage, Connected Components (CC), Enclosed Regions (ER), Basic Features (BF) and Curvelet Feature (CF)-based approaches are used to characterize signatures. Considering the extracted feature vectors, an interval data value is created for each feature extracted from every individual's signatures as an interval-valued symbolic data. This process results in a signature model for each individual that consists of a set of interval values. A similarity measure is proposed as the classifier in this paper. The interval-valued symbolic representation based method has never been used for signature verification considering Indian script signatures. Therefore, to evaluate the proposed method, a Hindi signature database consisting of 2400 (100x24) genuine signatures and 3000 (100x30) skilled forgeries is employed for experimentation. Concerning this large Hindi signature dataset, the highest verification accuracy of 91.83% was obtained on a joint feature set considering all four sets of features, while 2.5%, 13.84% and 8.17% of FAR (False Acceptance Rate), FRR (False Rejection Rate), and AER (Average Error Rate) were achieved, respectively.
This paper presents a new approach for online signature verification that exploits the potential of local stability information in handwritten signatures. Different from previous models, this approach classifies a signature using a multidomain strategy. A signature is first split into different segments based on the stability model of a signer. Then, according to the stability model, for each segment, the most profitable domain of representation for verification purposes is detected. In the verification stage, the authenticity of each segment of the unknown signature is evaluated in the most profitable domain of representation. The authenticity of the unknown signature is then determined by combining local verification decisions. The study was carried out on the signatures in the SUSIG database, and the experimental results, thus, obtained confirm the effectiveness of the proposed approach, when compared with others in the literature.
Effective and efficient generation of keypoints from an image is a well-studied problem in the literature and forms the basis of numerous Computer Vision applications. Established leaders in the field are the SIFT and SURF algorithms which exhibit great performance under a variety of image transformations, with SURF in particular considered as the most computationally efficient amongst the high-performance methods to date. In this paper we propose BRISK1, a novel method for keypoint detection, description and matching. A comprehensive evaluation on benchmark datasets reveals BRISK's adaptive, high quality performance as in state-of-the-art algorithms, albeit at a dramatically lower computational cost (an order of magnitude faster than SURF in cases). The key to speed lies in the application of a novel scale-space FAST-based detector in combination with the assembly of a bit-string descriptor from intensity comparisons retrieved by dedicated sampling of each keypoint neighborhood.
This paper presents a set of geometric signature features for offline automatic signature verification based on the description of the signature envelope and the interior stroke distribution in polar and Cartesian coordinates. The features have been calculated using 16 bits fixed-point arithmetic and tested with different classifiers, such as hidden Markov models, support vector machines, and Euclidean distance classifier. The experiments have shown promising results in the task of discriminating random and simple forgeries.
In recent years, along with the extraordinary diffusion of the Internet and a growing need for personal verification in many daily applications, automatic signature verification is being considered with renewed interest. This paper presents the state of the art in automatic signature verification. It addresses the most valuable results obtained so far and highlights the most profitable directions of research to date. It includes a comprehensive bibliography of more than 300 selected references as an aid for researchers working in the field.
We propose a new camera-based biometric: visual signature identification. We discuss the importance of the parameterization of the signatures in order to achieve good classification results, independently of variations in the position of the camera with respect to the writing surface. We show that affine arc-length parameterization performs better than conventional time and Euclidean arc-length ones. We find that the system verification performance is better than 4 percent error on skilled forgeries and 1 percent error on random forgeries, and that its recognition performance is better than 1 percent error rate, comparable to the best camera-based biometrics.
We study the question of feature sets for robust visual object recognition, adopting linear SVM based human detection as a test case. After reviewing existing edge and gradient based descriptors, we show experimentally that grids of Histograms of Oriented Gradient (HOG) descriptors significantly outperform existing feature sets for human detection. We study the influence of each stage of the computation on performance, concluding that fine-scale gradients, fine orientation binning, relatively coarse spatial binning, and high-quality local contrast normalization in overlapping descriptor blocks are all important for good results. The new approach gives near-perfect separation on the original MIT pedestrian database, so we introduce a more challenging dataset containing over 1800 annotated human images with a large range of pose variations and backgrounds.
A new approach for static signature verification is presented in this paper. The approach uses optical flow to estimate local stability among signatures. In the enrollment stage, optical flow is used to define a stability model of the genuine signatures for each signer. In the verification stage, the stability between the unknown signature and each one of the reference signatures is estimated and consistency with the stability model of the signer is evaluated. The experimental results, carried out on the signatures in the GPDS database, demonstrate the effectiveness of the new approach.
A graph matching approach to off-line signature verification is presented. Each of the signature images being compared is represented as a point set, which includes the local extremas of various types along the signature contours. Graph matching involves a deformation measure and a mapping function between point sets. Multiresolution signature features, as computed by gradient, structural and concavity features are used to measure local correspondence. Deformation and similarity scores are combined to make the final decision. The method performs better than previous off-line methods and is comparable to that of on-line systems
In this work we present a strategy for off-line signature verification. It takes into account a writer-independent model which reduces the pattern recognition problem to a 2-class problem, hence, makes it possible to build robust signature verification systems even when few signatures per writer are available. Receiver operating characteristic (ROC) curves are used to improve the performance of the proposed system . The contribution of this paper is two-fold. First of all, we analyze the impacts of choosing different fusion strategies to combine the partial decisions yielded by the SVM classifiers. Then ROC produced by different classifiers are combined using maximum likelihood analysis, producing an ROC combined classifier. Through comprehensive experiments on a database composed of 100 writers, we demonstrate that the ROC combined classifier based on the writer-independent approach can reduce considerably false rejection rate while keeping false acceptance rates at acceptable levels.
This paper deals with a new technique for automatic segmentation of unconstrained handwritten connected numerals. To take care of variability involved in the writing style of different individuals a robust scheme is presented here. The scheme is mainly based on features obtained from a concept based on water reservoir. A reservoir is a metaphor to illustrate the region where numerals touch. Reservoir is obtained by considering accumulation of water poured from the top or from the bottom of the numerals. At first, considering reservoir location and size, touching position (top, middle or bottom) is decided. Next, analyzing the reservoir boundary, touching position and topological features of the touching pattern, the best cutting point is determined. Finally, combined with morphological structural features the cutting path for segmentation is generated. The proposed scheme is tested on French bank check data and an accuracy about 94.8% is obtained from the system.
This paper is concerned with off-line signature verification. Four different types of pattern representation schemes have been implemented, viz., geometric features, moment-based representations, envelope characteristics and tree-structured Wavelet features. The individual feature components in a representation are weighed by their pattern characterization capability using Genetic Algorithms. The conclusions of the four subsystems (each depending on a representation scheme) are combined to form a final decision on the validity of signature. Threshold-based classifiers (including the traditional confidence-interval classifier), neighbourhood classifiers and their combinations were studied. Benefits of using forged signatures for training purposes have been assessed. Experimental results show that combination of the feature-based classifiers increases verification accuracy.
In this work we address two important issues of off-line signature verification. The first one regards feature extraction. We introduce a new graphometric feature set that considers the curvature of the most important segments, perceptually speaking, of the signature. The idea is to simulate the shape of the signature by using Bezier curves and then extract features from these curves. The second important aspect is the use of an ensemble of classifiers based on graphometric features to improve the reliability of the classification, hence reducing the false acceptance. The ensemble was built using a standard genetic algorithm and different fitness functions were assessed to drive the search. Two different scenarios were considered in our experiments. In the former, we assume that only genuine signatures and random forgeries are available to guide the search. In the latter, on the other hand, we assume that simple and simulated forgeries also are available during the optimization of the ensemble. The pool of base classifiers is trained using only genuine signatures and random forgeries. Thorough experiments were conduct on a database composed of 100 writers and the results compare favorably.
There are inevitable variations in the signature patterns written by the same person. The variations can occur in the shape or in the relative positions of the characteristic features. In this paper, two methods are proposed to track the variations. Given the set of training signature samples, the first method measures the positional variations of the one-dimensional projection profiles of the signature patterns; and the second method determines the variations in relative stroke positions in the two-dimension signature patterns. The statistics on these variations are determined from the training set. Given a signature to be verified, the positional displacements are determined and the authenticity is decided based on the statistics of the training samples. For the purpose of comparison, two existing methods proposed by other researchers were implemented and tested on the same database. Furthermore, two volunteers were recruited to perform the same verification task. Results show that the proposed system compares favorably with other methods and outperforms the volunteers.
We describe a method for on-line handwritten signature verification. The signatures are acquired using a digitizing tablet which captures both dynamic and spatial information of the writing. After preprocessing the signature, several features are extracted. The authenticity of a writer is determined by comparing an input signature to a stored reference set (template) consisting of three signatures. The similarity between an input signature and the reference set is computed using string matching and the similarity value is compared to a threshold. Several approaches for obtaining the optimal threshold value from the reference set are investigated. The best result yields a false reject rate of 2.8% and a false accept rate of 1.6%. Experiments on a database containing a total of 1232 signatures of 102 individuals show that writer-dependent thresholds yield better results than using a common threshold.
In this paper a method for off-line signature verification based on geometric feature extraction and neural network classification is proposed. The role of signature shape description and shape similarity measure is discussed in the context of signature recognition and verification. Geometric features of input signature image are simultaneously examined under several scales by a neural network classifier. An overall match rating is generated by combining the outputs at each scale. Artificially generated genuine and forgery samples from enrollment reference signatures are used to train the network, which allows definite training control and at the same time significantly reduces the number of enrollment samples required to achieve a good performance. Experiments show that 90% correct classification rate can be achieved on a database of over 3000 signature images.
An approach to off-line signature verification, one with an on-line flavor, is described. A sequence of data is obtained by tracing the exterior contour of the sig- nature which allows the application of string-matching algorithms. The upper and lower contours of the signa- ture are first determined by ignoring small gaps between signature components. The contours are combined into a single sequence so as to define a pseudo-writing path. To match two signatures a non-linear normalization method, viz., dynamic time warping, is applied to seg- ment them into curves. Shape descriptors based on Zernike moments are extracted as features from each segment. A harmonic distance is used for measuring signature similarity. Performance is significantly bet- ter than that of a word-shape based signature verifica- tion method. When the two methods are combined, the overall performance is significantly better than either method alone. With a database of 1320 genuines and 1320 forgeries the combination method has an accuracy of 95% (with 20% rejection) which is comparable to that of on-line systems.
The current need for large databases to evaluate automatic biometric recognition systems has motivated the developing of the GPDS-960 corpus, an off-line handwritten signature database which contains 24 genuine signatures and 30 forgeries of 960 individuals. This paper describes the GPDS signature corpus, gives details about the acquisition protocols and presents preliminary verification results obtained using the GPDS data.
In this article, a new approach to offline signature verification, based on a general-purpose wide baseline matching methodology,
is proposed. Instead of detecting and matching geometric, signature-dependent features, as it is usually done, in the proposed
approach local interest points are detected in the signature images, then local descriptors are computed in the neighborhood
of these points, and afterwards these descriptors are compared using local and global matching procedures. The final verification
is carried out using a Bayes classifier. It is important to remark that the local interest points do not correspond to any
signature-dependent fiducial point, but to local maxima in a scale-space representation of the signature images. The proposed
system is validated using the GPDS signature database, where it achieves a FRR of 16.4% and a FAR of 14.2%.
This paper describes a novel approach for signature verication and identication in an oine environment based on a quasi-multiresolution technique using GSC (Gradient, Structural and Concavity) features for feature extraction. These features when used at the word level, instead of the character level, yield promising results with accuracies as high as 78% and 93% for verication and identication, respectively. This method was successfully employed in our previous theory of individuality of handwriting devel- oped at CEDAR | based on obtaining within and between writer statistical distance distributions. In this paper, exploring signature verication and identication as oine handwriting verication and identication tasks respectively, we depict a mapping from the handwriting domain to the signature domain.
A method for the automatic verification of online handwritten signatures using both global and local features is described.
The global and local features capture various aspects of signature shape and dynamics of signature production. We demonstrate
that adding a local feature based on the signature likelihood obtained from Hidden Markov Models (HMM), to the global features
of a signature, significantly improves the performance of verification. The current version of the program has 2.5% equal
error rate. At the 1% false rejection (FR) point, the addition of the local information to the algorithm with only global
features reduced the false acceptance (FA) rate from 13% to 5%.
The paper presents a novel set of features based on surroundedness property of a signature (image in binary form) for off-line signature verification. The proposed feature set describes the shape of a signature in terms of spatial distribution of black pixels around a candidate pixel (on the signature). It also provides a measure of texture through the correlation among signature pixels in the neighborhood of that candidate pixel. So the proposed feature set is unique in the sense that it contains both shape and texture property unlike most of the earlier proposed features for off-line signature verification. Since the features are proposed based on intuitive idea of the problem, evaluation of features by various feature selection techniques has also been sought to get a compact set of features. To examine the efficacy of the proposed features, two popular classifiers namely, multilayer perceptron and support vector machine are implemented and tested on two publicly available database namely, GPDS300 corpus and CEDAR signature database.
This paper is concerned with signature verification. Three different types of global features have been used for the classification of signatures. Feed-forward neural net based classifiers have been used. The features used for the classification are projection moments and upper and lower envelope based characteristics. Output of the three classifiers is combined using a connectionist scheme. Combination of these feature based classifiers for signature verification is the unique feature of this work. Experimental results show that combination of the classifiers increases reliability of the recognition results.
The authors propose a statistical model for signature verification
by computer. The model recognizes that repeated signatures by the owner
are similar but not identical. The model consists of a template
signature for each individual, and several factors which allow for
variations in each rendition of this template. These variations include
the speed of writing, as well as slowly varying affine transformations
size as size, rotation and shear. The estimated template represents the
mean of a sample of signatures from an individual, and the variations in
the factors can be used to establish several measures of variance. These
quantitative measures are essential for reliable signature verification
Automatic on-line signature verification is an intriguing
intellectual challenge with many practical applications. I review the
context of this problem and then describe my own approach to it, which
breaks with tradition by relying primarily on the detailed shape of a
signature for its automatic verification, rather than relying primarily
on the pen dynamics during the production of the signature. I propose a
robust, reliable, and elastic local-shape-based model for handwritten
on-line curves; this model is generated by first parameterizing each
on-line curve over its normalized arc-length and then representing along
the length of the curve, in a moving coordinate frame, measures of the
curve within a sliding window that are analogous to the position of the
center of mass, the torque exerted by a force, and the moments of
inertia of a mass distribution about its center of mass. Further I
suggest the weighted and biased harmonic mean as a graceful mechanism of
combining errors from multiple models of which at least one model is
applicable but not necessarily more than one model is applicable,
recommending that each signature be represented by multiple models,
these models, perhaps, local and global, shape based and dynamics based.
Finally, I outline a signature-verification algorithm that I have
implemented and tested successfully both on databases and in live
experiments
Off-line handwritten signature gpds-960 corpus
- F Vargas
- M Ferrer
- C Travieso
- J Alonso
F. Vargas, M. Ferrer, C. Travieso, and J. Alonso, "Off-line handwritten
signature gpds-960 corpus," in ICDAR, vol. 2, 2007, pp. 764-768.
Offline signature verification using local interest points and descriptors
- J Ruiz Del Solar
- C Devia
- P Loncomilla
- F Concha
J. Ruiz del Solar, C. Devia, P. Loncomilla, and F. Concha, "Offline
signature verification using local interest points and descriptors," in
CIARP, 2008, pp. 22-29.