Figure 8 - uploaded by Reihan Alinia Lat
Content may be subject to copyright.
Histograms of positive and negative similarity distribution on the evaluating result for CASIA-Iris-Thousand.
Source publication
In recent years, the topic of contactless biometric identification has gained considerable traction due to the COVID-19 pandemic. One of the most well-known identification technologies is iris recognition. Determining the classification threshold for large datasets of iris images remains challenging. To solve this issue, it is essential to extract...
Contexts in source publication
Context 1
... histogram visually compares how the proposed method with the margin-based loss functions can distinguish iris feature vectors. We can see a clear decision margin distinguished in Figure 8, where the positive similarities for ArcFace are more gathered to the right of the figure, and the overlapping area is smaller. Though Figure 9 is not as clear as Figure 8, we also see a more narrow distribution for CosFace and ArcFace positive similarities. ...
Context 2
... can see a clear decision margin distinguished in Figure 8, where the positive similarities for ArcFace are more gathered to the right of the figure, and the overlapping area is smaller. Though Figure 9 is not as clear as Figure 8, we also see a more narrow distribution for CosFace and ArcFace positive similarities. As illustrated in Figures 8 and 9, ArcFace + Triplet is the best among all of them because there is a smaller overlap area between the red and blue distributions, and its positive distribution is more tended to the right than the other one. ...
Context 3
... Figure 9 is not as clear as Figure 8, we also see a more narrow distribution for CosFace and ArcFace positive similarities. As illustrated in Figures 8 and 9, ArcFace + Triplet is the best among all of them because there is a smaller overlap area between the red and blue distributions, and its positive distribution is more tended to the right than the other one. SoftMax loss is worst at separation. ...
Similar publications
A Biometric system provides automatic identification of an individual based on a unique feature or characteristics possessed by the individual. Iris recognition is one of the important biometrics recognition system that identify people based on the iris. Among, the biometric system iris recognition is the best and most reliable and accurate. The ai...
Citations
... Lat et al. [13] aimed to solve the problem of determining the classification threshold for large datasets of iris images and extracting more discriminatory features from as many iris images as possible. The paper proposes a novel iris identification framework that integrates the lightweight Mo-bileNet architecture with customized ArcFace and Triplet loss functions. ...
In this paper, we discuss our proposed unified approach to iris recognition called the SwinIris. This approach works efficiently when combing a tuned version of the original Swin Transformer with a set of iris recognition processes. While the original Swin Transformer has recently been used on different biometric modalities due to its competitive advantage over other architectures, it has not been used for iris recognition. Thus, in our work, our proposed deep learning architecture is using a pre-trained Swin Transformer model that is fine-tuned with a set of linear layers. This model is a set of algorithmic aspects that achieve competitive iris-matching accuracy when using any of the selected iris databases selected to test our approach. Specifically, our proposed SwinIris Transformer-based iris recognition system is composed of four modules, namely, the eye detection, iris detection, iris segmentation, and iris classification modules. The proposed system commences with a detection process that aims to identify eyes within the camera-captured original iris images. Subsequently, the iris detection process identifies the iris patterns within the detected iris images to ensure that they are present and can be segmented. The third module involves iris segmentation, which extracts iris features utilized by the fourth and final module that matches iris images using the SwinIris-based Transformer model. The performance of the proposed system is evaluated on small- and large-scale iris datasets, including the CASIA-Iris- Thousand, CASIA-Iris-Lamp, CASIA-IntervalV4, and CASIA- IntervalV3. Our proposed model has a competitive iris classification accuracy when compared to various academic state-of-the-art methodologies, resulting in a classification performance ranging from 95.14% to 99.56%.
... The precision of IR is contingent upon the precision of iris segmentation, which involves the isolation of the iris area from the remaining portion of the ocular image. The discipline of biometrics pertains to the process of verifying and validating the identity of individuals by means of their distinct biological and behavioral traits [2]. Numerous studies concentrate on contemporary developments in identifying the most essential biometric features, with particular attention to techniques for iris segmentation and recognition processing. ...
Biometric recognition is essential for identifying people in security, surveillance, and mobile device authentication. Iris recognition (IR) biometrics is exact because it uses unique iris patterns to identify individuals. Iris segmentation, which isolates the iris from the rest of the ocular image, determines iris identification accuracy. The main problem is concerned with selecting the best deep learning (DL) algorithm to classify and estimate biometric iris biometric iris. This study proposed a comprehensive review of DL-based methods to improve biometric iris segmentation and recognition. It also evaluates reliability, specificity, memory, and F-score. It was reviewed with iris image analysis, edge detection, and classification literature. DL improves iris segmentation and identification in biometric authentication, especially when combined with additional biometric modalities like fingerprint fusion. Besides, that DL in iris detection requires large training datasets and is challenging to use with noisy or low-quality photos. In addition, it examines DL for iris segmentation and identification efforts to improve biometric application understanding. It also suggests ways to improve precision and reliability. DL may be used in biometric identification; however, further study is needed to overcome current limits and improve IR processes.
... Due to its numerous applications in security from airports to homeland security border control, iris recognition has been active research area of study in last few years [1]. In the past, various iris recognition features and algorithms have been described. ...
... Traditional eye-iris detection systems are based on the least space between a person and a pictural-device which is less than 1m. So, these systems are based on high user cooperation but the drawback is a person has to pause and look at the sensor-device [6]. The permanence of eye-iris attributes for a person along the living makes the eye-iris detection the preferred one for individual identification [7,8]. ...
Iris-biometrics are an alternative way of authenticating and identifying a person because biometric identifiers are unique to people. This paper introduces a method aims to efficient human identification by enhanced iris detection method within acceptable time. After preparing various type of images, then perform a series of pre-processing steps and standardize them, after that use Uni-Net learning, so identify the human by Navie-Bays method is the last step based on the output of Uni-Net which is role as feature extractor for the iris part and another sub-net for non-iris part that may involve identification-outcome. The outcome of this method looked good compared to some high-level methods, so, was accuracy-rate 9855, 99.25, and 99.81 for CASIA-v4, ITT-Delhi, and MMU-database respectively. Also, this paper introduces a method of iris recognition using CNN model which is improved the preprocessed patterns that together from dataset applied some procedures to develop them based on techniques of equalization and acclimate contrast ones. After that characteristic extracted and classified using CNN that comprises of 10 layers with back-propagation schema and adjusted moment evaluation Adam-optimizer for modernize weights. The overall accuracy was 95.31% with utilization time 17.58 (mints) for training-model.
... Multimodal biometric frameworks combine the features introduced by various biometric wellsprings of data. The proposed approach presents a multimodal biometric framework dependent on the fusion of FKP and Iris [1] at the match score level. The features of FKP [2] are captured by the fusion of feature vectors by applying SIFT [3] and SURF [4]. ...
Biometric is the term for measuring human. If the term is divided into 2 parts: Bio means life and metric means measurement. The measurement of human through different computational methods is done to authorize a person. This measurement can be done via single Biometric or by using the combination of different biometric traits. The combination of multiple Biometrics is termed as Biometric Fusion. It provides a reliable and secure authentication of a person at a higher accuracy. It has been introduced in the UIDIA framework in India (AADHAR: Association for Development and Health Action in Rural) and different nations to figure out which Biometric characteristics are suitable enough to authenticate the Human identity. Fusion in biometric frameworks, especially FKP (Finger-Knuckle Print) and iris, demonstrated to be a solid multimodal as a secure framework. The proposed approach demonstrates a proficient and strong multimodal biometric framework that utilizes FKP and iris as biometric modalities for authentication utilizing scale-invariant feature transform (SIFT) and speeded up robust features (SURF). Log-Gabor Wavelet is utilized to extricate the iris feature set. From the extracted region, features are computed using Principal Component Analysis (PCA). Both biometric modalities, FKP, and iris are combined at the match score level. The matching is performed using a Neuro-Fuzzy neural network classifier. The execution and accuracy of the proposed framework are tested on the open database Poly-U, CASIA, and an accuracy of 99.68% is achieved. The accuracy is higher as compared to the single Biometric. The Neuro Fuzzy approach is also tested with comparison to other classifiers and the accuracy is 98%. So, the fusion mechanism implemented using Neuro Fuzzy classifier gives the best accuracy as compared to other classifiers. The framework is implemented in MATLAB 7.10.
Certain biological information or behavioral information of a person can achieve the effect of characterizing an individual, and by combining the computer to extract the corresponding information, identity authentication is achieved. In a variety of biometrics, iris relative to fingerprints, handwriting and face, belongs to the structure within the human eye, if you want to steal is very difficult, in order to improve the safety factor, so the iris is used for authentication to achieve iris recognition. This study is based on deep learning iris recognition matching, in order to be able to effectively improve the accuracy of iris recognition, experiments are carried out. Evaluation metrics are performed through Hamming distance to calculate the correct recognition rate to ensure that the iris information can be accurately represented. This study mainly uses the improved PCHIP-LMD algorithm and CNN algorithm, the LMD algorithm is more context- aware, has better generalization ability, flexibility and scalability, while the CNN algorithm has the advantages of local awareness, parameter sharing and automatic parameter learning. In this study, we compare the correct recognition rate of iris recognition between improved PCHIP-LMD and CNN algorithms and get the conclusion that the correct recognition rate of the improved PCHIP-LMD algorithm is only 78%, which is much smaller than that of the CNN algorithm which is 92%, and we get the conclusion that LMD algorithm is suitable for iris recognition with few samples, and it is more suitable to use CNN algorithm when the sample images are too many. CNN algorithm. With the development of technology, the application of iris recognition will be more and more, I believe that soon will be widely popularized in daily life and work.
