Palm Dorsal Vein Research Articles

A multimodal architecture using Adapt‐HKFCT segmentation and feature‐based chaos integrated deep neural networks (Chaos‐DNN‐SPOA) for contactless biometricpalm vein recognition system

In the recent past, the fusion of various unimodal biometrics has gained increasing attention from researchers dedicated to the use of practical biometrics. In this paper, a Chaos Integrated Deep Neural Networks (Chaos-DNN) using Sandpiper Optimization Algorithm (SPOA) is proposed to enhance the performance of the multimodal contactless biometric pattern recognition system. The most significant advantage of palm vein and palm dorsal vein recognition is that it provides relatively high accuracy, reliability and also liveness detection. In this recognition process, the palm and its dorsal vein images are segmented using multilevel segmentation of region of interest (ROI) depending on Adaptive Hyper Kernel Optimized Fuzzy Clustering Technique (Adapt-HKFCT), and then ROI extracted based on the valley points among the index and ring finger using the Knuckle points. Then, the features of the ROI amid the index and ring finger are extracted using centre-symmetric local binary pattern algorithm and fed to the Chaos-DNN for training and classification. The efficiency of the features is optimized using SPOA. The extracted feature points help in authenticating a person using his/her chosen biometric traits for security purposes. The objective of this system is to increase the efficiency of the biometric system, and the performance is calculated depending on equal error rate, correct recognition rate, decidability index, false acceptance rate and false rejection rate. The proposed algorithm has been implemented in MATLAB platform. The experimental outcomes demonstrate that the proposed palm vein recognition depending Adapt-HKFCT with Chaos-DNN using SPOA method (PVR-AHKFCT-CDNN-SPOA) attains higher performance metrics with an accuracy of 98.3% and is also more efficient likened to the other existing methods, such as K Nearest Neighbour with Particle Swarm Optimization (PVR-KNN-PSO), Fuzzy Brain Storm Optimization based on Adaptive Thresholding (PVR-FBSO-AT), multiscale local binary pattern with ant colony optimization (PVR-MSLBP-ACO) and Deep Learning with Bayesian Optimization (PVR-DL-BO).

Multibiometric Authentication System Using Slap Fingerprints, Palm Dorsal Vein, and Hand Geometry

In this paper, a multibiometric system that fuses slap fingerprints, palm dorsal vein, and hand geometry for accurate person authentication is proposed. The proposed system simultaneously acquires slap images and infrared (IR) hand dorsal image from which slap fingerprints, palm dorsal veins, and IR hand geometry are extracted. Simultaneous acquisition reduces the acquisition time and helps to improve user acceptability. The slap segmentation is accomplished using the knowledge of the approximate finger location and hand type (either left or right) obtained from the simultaneously acquired IR hand dorsal image. Multibiometric fusion based on serial methodology has been proposed for consolidating the matching scores of slap fingerprints, palm dorsal vein, and IR hand geometry. It ensures better performance in terms of accuracy and time. Experimental results indicate that authentication using slap fingerprints can be improved by incorporating the knowledge from IR hand images. Further, it depicts that the fusion of slap fingerprint, palm dorsal vein, and IR hand geometry can help to achieve the best performance.

Multi-size patch based collaborative representation for Palm Dorsa Vein Pattern recognition by enhanced ensemble learning with modified interactive artificial bee colony algorithm

This paper proposes a novel method, Multi-Size patch based Collaborative Representation based Classification (CRC) strategy by Enhanced Ensemble Learning, for palm dorsa vein pattern (PDVP) based human recognition employing thermal imaging. This thermal PDVP imaging based human recognition methodology has been specifically employed to encounter the challenging crisis of intrusion posed by imposters. To address the Small Sample Size (SSS) problem, intrinsic to many biometric applications, each image is transformed into multiple patches, leading to an increase in the total number of samples. In a bid to make the classification strategy less sensitive to the choice of patch-size, the present paper proposes a new enhanced ensemble learning for the patch based CRC (PCRC) algorithm, where margin maximization is carried out using exponential squared loss minimization. This work also proposes how this loss minimization can be achieved by a stochastic optimization algorithm and solves this problem using artificial bee colony (ABC) algorithm. In this context, a new ABC variant, called modified interactive artificial bee colony (MI-ABC) algorithm, has also been proposed, which has been demonstrated to outperform the basic ABC and its several modern variants. The proposed methodology has been implemented on a well–structured real database, developed in our laboratory using real subjects, and the results obtained in implementation phase clearly demonstrate that our proposed method could outperform its several competitors and achieve substantially high classification rates, for the problem under consideration.

Multi-modal fusion of palm-dorsa vein pattern for accurate personal authentication

This paper proposes an efficient multi-modal authentication system which makes use of palm-dorsa vein pattern. There are four levels of fusion in the system and they are multi-algorithm fusion, data fusion, feature fusion and score fusion. Multi-algorithm fusion is applied to extract genuine vein patterns from a vein image by using various vein extraction algorithms. All false vein patterns are eliminated from the extracted patterns through data fusion. Three types of features are obtained from each extracted vein pattern and they are shape features, minutiae and features obtained from hand boundary shape. Third level of fusion is at feature level to fuse minutiae and shape features. Finally, fused features and hand boundary shape features are matched to obtain matching scores which are fused at score level. The proposed system has been tested on the database acquired from 4120 images of 1030 subjects. It has achieved an accuracy of 100%. Experimental results reveal that it performs better than other existing systems.

Palm-dorsal vein recognition based on uniform discrete curvelet transformation

Palm-dorsal vein recognition using Uniform Discrete Curvelet Transform(UDCT) was proposed in this paper.With the palm-dorsal Region Of Interest(ROI) extraction and image preprocessing,UDCT of the curvelet Transform was used on ROI.Then,the curvelet coefficients phase variance was encoded.Finally,the Chi-square distance of histogram of the coding was used for vein recognition.The experimental results show that this proposed method can identify palm-dorsal vein images with high robustness and high speed even with poor-quality images.

Palm-Dorsal Vein Recognition Method Based on Histogram of Local Gabor Phase XOR Pattern with Second Identification

This paper proposes a palm-dorsal vein recognition method with local Gabor phase features, which includes a second identification for more accuracy. First, we extract quadrant-bit codes from the 2D Gabor transformation of a vein image. Then using the Histogram of the Local Gabor Phase XOR Pattern (HLGPXP) obtains the vein texture features, which combines the global information and the local information. Finally, the chi-square distance is adopted for recognition. Using the texture features based on the local Gabor codes above, the Second Identification (SI) segments the vein images and regards the non-overlap degree between images as a matching criterion. The experimental results show the Error Equation Rate (EER) of our method (HLGPXP-SI) decreases by 11.7 %, 4.8 % respectively than Modified Local Binary Pattern (MLBP) [1], Local Gabor Binary Pattern (LGBP) [2] on Database A (204 high-quality palm-dorsal vein images from 68 hands), and on Database B (400 low-quality palm-dorsal vein images from 100 hands), it decreases by 18.94 %, 15.51 % respectively than Selected Gabor Phase and Amplitude Features (SGPAF) [3], Direct Gabor Phase Coding (DGPC) [4].

An Image Quality Assessment Algorithm for Palm-Dorsa Vein Based on Multi-Feature Fusion

In order to acquire more feature information in captured vein image with high-quality, an image quality assessment algorithm for palm-dorsa vein is presented based on multi-feature fusion. According to the statistical and structure properties of image, we can acquire the good vein image by adjusting near-infrared LED light exposure duty cycle combined with computing the four characteristic parameters of gray variance, information entropy, cross point and area of effect and then fusing those according to weights. In the end, an experimental case is given and the assessment results prove that this algorithm is efficient.

Comprehensive analysis of spectral minutiae for vein pattern recognition

Similar to biometric fingerprint recognition, characteristic minutiae points – here end and branch points – can be extracted from skeletonised vein images to distinguish individuals. An approach to extract those vein minutiae and to transform them into a fixed-length, translation and scale invariant representation where rotations can be easily compensated is presented in this study. The proposed solution based on spectral minutiae is evaluated against other comparison strategies on three different datasets of wrist and palm dorsal vein samples. The authors' analysis shows a competitive biometric performance while producing features that are compatible with state-of-the-art template protection systems. In addition, a modified and more distinctive, but not transform or rotation invariant, representation is proposed and evaluated.

Palm-dorsa vein recognition based on two-dimensional Fisher linear discriminant

The palm-dorsa vein recognition uses non-contact technology.A locating algorithm was presented in order to avoid the interference brought by the rotation and translation of the palm-dorsa when collecting pictures.This method ultimately intercepted a rectangle on the palm-dorsa containing the information of vein as much as it can.The feature points of palm-dorsa edge were located by the location method based on unchanged feature points,and then the effective region was obtained.Experimental results show that the algorithm is self-adaptive,accurate and fast.To solve the problem that the within-class scatter matrix is always singular based on Fisher Linear Discriminant(FLD),a new way based on Two-Dimensional FLD(2DFLD)was used in the palm-dorsa vein recognition.The image matrix was directly projected to avoid high dimension operation.In the experiments,2DFLD was applied to extract the vein feature subspace from palm-dorsa vein database.The test sample images to be recognized were projected on small dimension subspace.Lastly,a nearest neighbor classifier for palm-dorsa vein matching based on Euclidean distance was used and the recognition rate reached as high as 98%.

Biometric Verification Using Thermal Images of Palm-Dorsa Vein Patterns

A novel approach to personal verification using the thermal images of palm-dorsa vein patterns is presented in this paper. The characteristics of the proposed method are that no prior knowledge about the objects is necessary and the parameters can be set automatically. In our work, an infrared (IR) camera is adopted as the input device to capture the thermal images of the palm-dorsa. In the proposed approach, two of the finger webs are automatically selected as the datum points to define the region of interest (ROI) on the thermal images. Within each ROI, feature points of the vein patterns (FPVPs) are extracted by modifying the basic tool of watershed transformation based on the properties of thermal images. According to the heat conduction law (the Fourier law), multiple features can be extracted from each FPVP for verification. Multiresolution representations of images with FPVPs are obtained using multiple multiresolution filters (MRFs) that extract the dominant points by filtering miscellaneous features for each FPVP. A hierarchical integrating function is then applied to integrate multiple features and multiresolution representations. The former is integrated by an inter-to-intra personal variation ratio and the latter is integrated by a positive Boolean function. We also introduce a logical and reasonable method to select a trained threshold for verification. Experiments were conducted using the thermal images of palm-dorsas and the results are satisfactory with an acceptable accuracy rate (FRR:2.3% and FAR:2.3%). The experimental results demonstrate that our proposed approach is valid and effective for vein-pattern verification.