FIGURE 5 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Source publication
![FIGURE 4. The parameters of a triangle of [3].](publication/348301837/figure/fig4/AS:977337575276548@1610026844982/The-parameters-of-a-triangle-of-3_Q320.jpg)
A simple fingerprint identification scheme compares an input fingerprint with all the fingerprints in the database to find any matching fingerprint. That is, the simple matching method considers all fingerprints in the database as candidates for a given input fingerprint. However, this simple matching method requires a lot of processing time. To re...
Context in source publication
Context 1
... compare the index value distributions between the Kavati et al.'s method and our method, we have normalized the index values which is shown in Figure 5. In the comparison we used FVC2002 DB1, where the x and y coordinates are the second and third components of the index vector, respectively. ...
Citations
... efficiency and accuracy of AFIS. Classical embedding algorithms generally focus on the geometric structures of fingerprint minutiae, e.g., triplets [1,18] and cylinders [5]. Nevertheless, these methods heavily rely on handcrafted rules to extract embedded features, thereby suffering from inferior robustness and limited generalization in large-scale automated fingerprint recognition scenarios. ...
... Fingerprint feature embedding plays a critical role in modern AFIS. Classical embedding methods are generally based on minutia triplets [1,18]or cylinder-code [5]. However, algorithms with these geometric structures heavily rely on handcrafted rules and complex design procedures that depress the performance of representation. ...
Deep learning has achieved remarkable results in fingerprint embedding, which plays a critical role in modern Automated Fingerprint Identification Systems. However, previous works including CNN-based and Transformer-based approaches fail to exploit the nonstructural data, such as topology and correlation in fingerprints, which is essential to facilitate the identifiability and robustness of embedding. To address this challenge, we propose a novel paradigm for fingerprint embedding, called Minutiae Relation-Aware model over Graph Neural Network (MRA-GNN). Our proposed approach incorporates a GNN-based framework in fingerprint embedding to encode the topology and correlation of fingerprints into descriptive features, achieving fingerprint representation in the form of graph embedding. Specifically, we reinterpret fingerprint data and their relative connections as vertices and edges respectively, and introduce a minutia graph and fingerprint graph to represent the topological relations and correlation structures of fingerprints. We equip MRA-GNN with a Topological relation Reasoning Module (TRM) and Correlation-Aware Module (CAM) to learn the fingerprint embedding from these graphs successfully. To tackle the over-smoothing problem in GNN models, we incorporate Feed-Forward Module and graph residual connections into proposed modules. The experimental results demonstrate that our proposed approach outperforms state-of-the-art methods on various fingerprint datasets, indicating the effectiveness of our approach in exploiting nonstructural information of fingerprints.
A sophisticated mathematical model known as neurosophic extends the vague concept to tackle
real-world issues and applications. The neutrosophic connection of the image can be harnessed to ascertain
its correlation pattern. This paper aims to employ the neutrosophic method for detecting correlations among
fingerprint images using neutrosophic-based pattern analysis. Additionally, it will propose four strategies for
identifying relationships within image data by employing the neutrosophic approach. The study explores the
four fundamental forms of fingerprint images and experiments with various α values. An α value of 0.99 or
higher is favored for image matching.
As an important identification method, fingerprint recognition has a wide range of applications. To make the fingerprint recognition system of a library more efficient and secure, a recognition technology based on the characteristic search algorithm is proposed, and the performance of the algorithm is analysed. When a reasonable threshold is set, the matching error rate of the algorithm can be controlled at a lower level, and the algorithm can also ensure a higher fingerprint and determine the overall accuracy. At the same time, three other identification algorithms of the same type are introduced: radio frequency fingerprinting, convolutional neural network and local binary pattern. In a comparative experiment, it was found that the characteristic search algorithm model had the highest accuracy, with a value of 94.8%. When dealing with the same amount of fingerprint data, the recognition time of the algorithm model was the shortest. In addition, the area under the curve value corresponding to the receiver operating characteristic curve of the algorithm was the largest, and its value was 0.94. It is well known that the performance of the characteristic search algorithm is optimal and can effectively improve the operation efficiency of a library fingerprint identification system.
Nowadays, both fingerprint and palmprint databases are massive and whose size has exceeded millions. Therefore, applying a filtering technique, such as indexing, is vital for automatic fingerprint/palmprint identification systems. Geometric distortion present in fingerprints and the creases in palmprints have a significant drop in recognition accuracy. Moreover, protecting an enrollment template is an important and challenging issue today. Template protection is a technique to convert an unprotected enrollment biometric template to a protected biometric template and is used to prevent the access of illegal users and attackers to the enrolled biometric template. Hence, in this paper, we propose a new feature called the middle of the triangle’s side (MTS) derived from each minutiae pair of a triangle-based representation to mitigate the negative effect of the geometric distortion and creases. Furthermore, they can be used as a feature transformation to protect templates. For computing MTSs, we first estimate the quality of input images and then extract reliable minutiae from the input images. After that, we apply the Delaunay triangulation of order k to minutiae for obtaining a triangle-based representation. Then, we calculate the median of sides of each triangle for extracting MTSs. To obtain the direction of each MTS, we use the direction difference between each minutiae pair placed in both vertices of the triangle’s side. This makes MTSs robust against fingerprint and palmprint rotation. Afterward, we obtain new triangles by connecting the MTSs of each triangle and weight feature vectors based on the quality of minutiae, and generate indices. Finally, we propose a new feature vector for triangles to increase the recognition accuracy. Experimental results on two public fingerprint databases containing distorted fingerprints, and two public palmprint databases containing latent prints, show that MTSs are more robust than minutiae against geometric distortion. Also, MTSs are secure, and its reason is that minutiae direction and location are changed. In addition, the number of MTSs is more than minutiae, making them more appropriate for prints with a low number of minutiae. Our experimental results show that MTSs and the proposed indexing algorithm can obtain good results for distorted fingerprints and latent palmprints.
Automatic fingerprint identification systems (AFIS) are among the most used people identification solutions. As the size of fingerprint databases is continuously growing, studying fingerprint indexing mechanisms is desirable to facilitate the search process in a large-scale database. This work presents a method for fingerprint indexing, which uses both exact and approximation methods of nearest neighbors (ANNs), which are very efficient in terms of runtime, even if they sacrifice a little accuracy by presenting approximate solutions. In the presented approach, searches with ANN methods are made from deep embedding vectors extracted from image databases using a convolutional neural network (CNN). In this work, a CNN ResNet18 was used to extract the deep feature embeddings vectors, and the vectors vary in size between 64, 96, and 128. The ANNs methods tested for the query step were ANNOY, NGT, HNSW, and Nanoflann. The results were quite promising when using the FVC fingerprint databases (2000, 2002, and 2004), once we reached 100% hits in the searches with a penetration rate of 1%, with very low run times.
