Finger vein recognition using minutia‐based alignment and local binary pattern‐based feature extraction

Abstract

With recent increases in security requirements, biometrics such as fingerprints, faces, and irises have been widely used in many recognition applications including door access control, personal authentication for computers, Internet banking, automatic teller machines, and border-crossing controls. Finger vein recognition uses the unique patterns of finger veins to identify individuals at a high level of accuracy. This article proposes a new finger vein recognition method using minutia-based alignment and local binary pattern (LBP)-based feature extraction. Our study makes three novelties compared to previous works. First, we use minutia points such as bifurcation and ending points of the finger vein region for image alignment. Second, instead of using the whole finger vein region, we use several extracted minutia points and a simple affine transform for alignment, which can be performed at fast computational speed. Third, after aligning the finger vein image based on minutia points, we extract a unique finger vein code using a LBP, which reduces false rejection error and thus the equal error rate (EER) significantly. Our resulting EER was 0.081% with a total processing time of 118.6 ms.

A Binary Code Learning Method Based on Class-neighborhood for Finger Vein Recognition

“…As show in the table, taking into consideration of matching accuracy and information entropy, k is selected as 60, and the best EER=0.512%. To verify the validity of the proposed method, in this experiment, state-of-the-art methods for finger vein recognition such as LBP [6], (2D) 2 FPCA [12], BLPOC [7], Gabor [4], HOG [8]and HOL [11]are implemented for comparison. Table 2 shows the receiver operating characteristics (ROC) curves derived from the above methods.…”

“…Many efforts are contributed to develop this technology and the technology has made remarkable progress with these efforts in the resent two decades. The representative methods include repeated line tracking by Miura [3], various feature extraction methods based on Gabor filter [4,5], local binary pattern (LBP)method based on local information [6], band-limited phase only correlation filter (BLPOC) [7], histogram of oriented gradients (HOG) descriptor [8], and various subspace learning methods, etc. These methods investigate various feature description for finger vein.…”

Reflection-type Finger Vein Recognition for Mobile Applications

“…16. Lee et al implemented finger-vein feature extraction based on minutia-based alignment and LBP [19]. Information about direction is the major feature of a finger vein.…”

Gender Attribute Mining with Hand-Dorsa Vein Image Based on Unsupervised Sparse Feature Learning

“…Driven by the fact that the subject-specified hand-vein information could be well represented by the four models, is that possible to obtain effective gender-specified representation so that accurate gender classification result would be generated with similar methods? Four representative methods involving mean curvature [3], (2D)2PCA [4], LBP [5], SIFT [6], which corresponds to the four identity recognition groups, are made attempt with the lab-made database to figure out answer to our puzzle, extremely low classification accuracy as shown in Table 1 fication and recognition task [7], [8], an unsupervised sparse feature learning model (USFL) to learn the statistical representation of specific vein information only differing in gender is proposed in this letter. The new feature learning model is easy to implement and free of complicated hyperparameter tuning (only the number of features to learn is tunable) when compared with the restricted Boltzmann machines (RBM) [9], denoising autoencoders [10] and sparse coding [11].…”