Texture Based Vein Biometrics for Human Identification: A Comparative Study

Abstract

Hand vein biometric is an important modality for human authentication and liveness detection in many applications. Reliable feature extraction is vital to any biometric system. Over the past years, two major categories of vein features, namely vein structures and vein image textures, were proposed for hand dorsal vein based biometric identification. Of them, texture features seem important as it can combine skin microtextures along with vein properties. In this study, we have performed a comparative study to identify potential texture features and feature-classifier combination that produce efficient vein biometric systems. Seven texture features (HOG, GABOR, GLCM, SSF, DWT, WPT, and LBP) and three multiclass classifiers (LDA, ESVM, and KNN) were explored towards the supervised identification of human from vein images. An experiment with 400 infrared (IR) hand images from 40 adults indicates the superior performance of the histogram of oriented gradients (HOG) and simple local statistical feature (SSF) with LDA and ESVM classifiers in terms of average accuracy (> 90%), average Fscore (> 58%) and average specificity (>93%). The decision-level fusion of the LDA and ESVM classifier with single texture features showed improved performances (by 2.2 to 13.2% of average Fscore) over individual classifier for human identification with IR hand vein images.

Improvement of confusion matrix for Hand Vein Recognition Based On Deep- Learning multi-classifier Decisions

“…Yuhang et al [32] introduced a comparatively good recognition effect, which the technique of extracting a hand vein pattern constructed on end and crossing points. Bashar et al [10] achieved proportional learning to identify feature-classifier mixture that creates well-organized vein biometric approaches. 7 texture and three multiclass classifiers were discovered near the managed ID of individuals from a vein.Lee et al [16] introduced feature mining outclasses the broadly used Gabor filters, which was appropriately wild for actual verification, and by comparing this, the proposed approach can result in an enhanced performance.…”

“…It is usually accepted before feature drawing out to reduce the noise influence on the consequent feature abstraction and to increase enactment. Toward adapt the main patterns into the necessary designs, the pre-processing operation will be approved with on the original patterns [10][11][12]. Depending on [13][14][15][16] deep learning techniques have been supported in image classification and responsibilities recovery.…”

Hybrid Feature Extractor Using Discrete Wavelet Transform and Histogram of Oriented Gradient on Convolutional-Neural-Network-Based Palm Vein Recognition

“…The process then continues to feature extraction, which can be performed based on two categories of low-level features, namely, structural and textural features. There are several methods for this category of features, such as supervised discriminative sparse principal component analysis neighborhood-preserving embedding (SDSPCA-NPE) [ 31 ], local binary pattern (LBP) [ 32 ], gray-level co-occurrence matrix (GLCM), and histogram of oriented gradient (HOG) [ 33 ]. Based on the results of [ 33 ], HOG showed the best result among the texture features that were extracted [ 33 ] due to its superiority in detecting the degree of differences among transformations and variants [ 34 ], although there are still some reports that low-level features are unrepresentative and unstable [ 35 ].…”

“…There are several methods for this category of features, such as supervised discriminative sparse principal component analysis neighborhood-preserving embedding (SDSPCA-NPE) [ 31 ], local binary pattern (LBP) [ 32 ], gray-level co-occurrence matrix (GLCM), and histogram of oriented gradient (HOG) [ 33 ]. Based on the results of [ 33 ], HOG showed the best result among the texture features that were extracted [ 33 ] due to its superiority in detecting the degree of differences among transformations and variants [ 34 ], although there are still some reports that low-level features are unrepresentative and unstable [ 35 ]. In order to handle this, methods to extract high-level features have been introduced, i.e., deep learning, and can obtain features automatically from a given dataset for each specific application.…”