Yiding Wang

Combining Spatial and Temporal Information for Gait Based Gender Classification

In this paper, we address the problem of gait based gender classification. The Gabor feature which is a new attempt for gait analysis, not only improves the robustness to the segmental noise, but also provides a feasible way to purge the additional influence factors like clothing and carrying condition changes before supervised learning. Furthermore, through the agency of Maximization of Mutual Information (MMI), the low dimensional discriminative representation is obtained as the Gabor-MMI feature. After that, gender related Gaussian Mixture Model-Hidden Markov Models (GMM-HMMs) are constructed for classification work. In this case, supervised learning reduces the dimension of parameter space, and significantly increases the gap between likelihoods of the gender models. In order to assess the performance of our proposed approach, we compare it with other methods on the standard CASIA Gait Databases (Dataset B). Experimental results demonstrate that our approach achieves better Correct Classification Rate (CCR) than the state of the art methods.

A robust method for near infrared face recognition based on extended local binary pattern

Face recognition is one of the most successful applications in biometric authentication. However, methods reported in the literature still suffer from some problems which prevent the further development in face recognition. This paper presents a novel robust method for face recognition under near infrared (NIR) lighting condition based on Extended Local Binary Pattern (ELBP), which solves the problems produced by variations of illumination rightly, since the NIR images are insensitive to variations of ambient lighting, and ELBP can extract adequate texture features form the NIR images. By combining the local feature vectors, a global feature vector is formed and as the global feature vectors extracted by ELBP operator often have very high dimensions, a classifier has been trained using the AdaBoost algorithm to select the most representative features for better performance and dimensionality reduction. Compared with the huge number of features produced by ELBP operator, only a small part of the features are selected in this paper, which saves much computation and time cost. The comparison with the results of classic algorithms proves the effectiveness of the proposed method.

Hand-dorsa vein recognition based on partition Local Binary Pattern

A new hand-dorsa vein recognition method based on Partition Local Binary Pattern (PLBP) is presented in this paper. The proposed method employs hand-dorsa vein images acquired from a low-cost, near infrared device. After preprocessing, the image is divided into sub-images. LBP uniform pattern features are extracted from all the sub-images, which are combined to form the feature vector for token vein texture features. The method is assessed using a similarity measure obtained by calculating the distance between the feature vectors of the tested sample and the target sample. The algorithm is tested on a database of 2040 images from 102 individuals built up by a custom-made acquisition device. The experimental results show that PLBP performs better than other features.

Study of hand-dorsa vein recognition

A new hand-dorsa vein recognition method based on Partition Local Binary Pattern (PLBP) is presented in this paper. The proposed method employs hand-dorsa vein images acquired from a low-cost, near infrared device. After preprocessing, the image is divided into sub-images. LBP uniform pattern features are extracted from all the sub-images, which are combined to form the feature vector for token vein texture features. The method is assessed using a similarity measure obtained by calculating the Chi square statistic between the feature vectors of the tested sample and the target sample. Integral histogram method, original LBP and Partition LBP with 16, 32, 64 sub-images are tested on a database of 2040 images from 102 individuals built up by a custom-made acquisition device. The experimental results show that Partition LBP performs better than original LBP, Circular Partition LBP performs better than Rectangular Partition LBP, and when the image was divided into 32 performs better than others.

Biometric identification based on low-quality hand vein pattern images

Vein pattern is used as biometric feature in recent 20 years and It attracts much attention from 2000. A complete vein pattern recognition system contains three key procedures, vein image collection, vein pattern segment and feature extraction. In this paper, we adopt low-cost collection devices and discuss all the three parts in details. First a novel image collection way is proposed, which could enhance the contrast. Then a denoising algorithm using wavelets thresholding based on Besov norm regularization is discussed. This algorithm could remove the high noise while do not hurt the contrast. Finally, two novel robust features specially designed for vein pattern are put forward. Experimental results show that our system is as successful as traditional high-price system. In conclusion, our research makes using low-cost devices to recognize vein patterns possible.

Hand vein recognition based on oriented gradient maps and local feature matching

The hand vein pattern as a biometric trait for identification has attracted increasing interests in recent years thanks to its properties of uniqueness, permanence, non-invasiveness as well as strong immunity against forgery. In this paper, we propose a novel approach for back of the hand vein recognition. It first makes use of Oriented Gradient Maps (OGMs) to represent the Near-Infrared (NIR) hand vein images, simultaneously highlighting the distinctiveness of vein patterns and texture of their surrounding corium, in contrast to the state-of-the-art studies that only focused on the segmented vein region. SIFT based local matching is then performed to associate the keypoints between corresponding OGM pairs of the same subject. The proposed approach was benchmarked on the NCUT database consisting of 2040 NIR hand vein images from 102 subjects. The experimental results clearly demonstrate the effectiveness of our approach.

Hand-Dorsa Vein Recognition by Matching Local Features of Multisource Keypoints

As an emerging biometric for people identification, the dorsal hand vein has received increasing attention in recent years due to the properties of being universal, unique, permanent, and contactless, and especially its simplicity of liveness detection and difficulty of forging. However, the dorsal hand vein is usually captured by near-infrared (NIR) sensors and the resulting image is of low contrast and shows a very sparse subcutaneous vascular network. Therefore, it does not offer sufficient distinctiveness in recognition particularly in the presence of large population. This paper proposes a novel approach to hand-dorsa vein recognition through matching local features of multiple sources. In contrast to current studies only concentrating on the hand vein network, we also make use of person dependent optical characteristics of the skin and subcutaneous tissue revealed by NIR hand-dorsa images and encode geometrical attributes of their landscapes, e.g., ridges, valleys, etc., through different quantities, such as cornerness and blobness, closely related to differential geometry. Specifically, the proposed method adopts an effective keypoint detection strategy to localize features on dorsal hand images, where the speciality of absorption and scattering of the entire dorsal hand is modeled as a combination of multiple (first-, second-, and third-) order gradients. These features comprehensively describe the discriminative clues of each dorsal hand. This method further robustly associates the corresponding keypoints between gallery and probe samples, and finally predicts the identity. Evaluated by extensive experiments, the proposed method achieves the best performance so far known on the North China University of Technology (NCUT) Part A dataset, showing its effectiveness. Additional results on NCUT Part B illustrate its generalization ability and robustness to low quality data.

Hand vein recognition based on multiple keypoints sets

Biometric authentication based on hand vein patterns has grown in popularity as a way to confirm personal identity. However, the imaging quality and variability of the vein images acquired by the near-infrared (NIR) device present challenges to achieve high classification accuracy. In this paper, a novel method for hand vein recognition by fusion of multiple sets of keypoints from the scale-invariant feature transform (SIFT) is proposed. While the use of SIFT enables classification to be unaffected by imaging quality and variability, the fusion reduces information redundancies and improves the discrimination power. The proposed method is tested on a database of 2040 images, and the experiment results show a good classification performance with a result of 97.95% recognition rate.

Face recognition with statistical Local Binary Patterns

In this work, we present a novel algorithm for face recognition named statistical Local Binary Patterns (sLBP). This is a further development of original Local Binary Pattern algorithm. Our method is applied for face recognition under visual light environment dealing with dramatically illumination varying on faces After a statistical analysis on the distribution probability of the gray-level difference values between neighbor pixels, a mapping function is proposed to encode a wide range of these values into three binary bits. Three extension LBP layers are then generated Finally the uniform pattern histograms of all these layers in every divided region are concatenated as an enhanced local feature vector of the face image. Experimental results on FERET face database show considerable effectiveness and robustness of our proposed method.

Hand-Dorsa Vein Recognition Based on Coded and Weighted Partition Local Binary Patterns

In this paper, a new feature descriptor is presented and proposed for personal verification based on near infrared images of hand-dorsa veins. This new feature descriptor is a modification of the previously proposed partition local binary patterns (PLBP) by adding feature weighting and error correction coding (ECC). While addition of feature weighting aims to reduce the influence of insignificant local binary patterns, addition of ECC aims to increase the distances between feature classes by utilizing the systematic redundancy that has been widely used to achieve reliable data transmission in noisy channels. Using a large database with more than two thousand hand-dorsa vein images, the resulting new feature descriptor, named Coded and Weighted PLBP (WCPLBP), is shown to be more effective than the original PLBP without feature weighting and ECC, and offers a better performance in recognition of hand-dorsa vein images with a correct recognition rate reaching approximately 99% using a simple nearest neighbor classifier.