Kejun Wang

Complete canonical correlation analysis with application to multi-view gait recognition

Canonical correlation analysis (CCA) is a well-known multivariate analysis method for quantifying the correlations between two sets of multidimensional variables. However, for multi-view gait recognition, it is difficult to directly apply CCA to deal with two sets of high-dimensional vectors because of computational complexity. Moreover, in such situation, the eigenmatrix of CCA is usually singular which makes the direct implementation of the CCA algorithm almost impossible. In practice, PCA or singular value decomposition is employed as a preprocessing step to solve these problems. Nevertheless, this strategy may discard dimensions that contain important discriminative information and correlation information. To overcome the shortcomings of CCA when dealing with two sets of high-dimensional vectors, we develop a novel method, named complete canonical correlation analysis (C3A). In our method, we first reformulate the traditional CCA so that we can avoid the computing of the inverse of a high-dimensional matrix. With the help of this reformulation, C3A further transforms the singular generalized eigensystem computation of CCA into two stable eigenvalue decomposition problems. Moreover, a feasible and effective method is proposed to alleviate the computational burden of high dimensional matrix for typical gait image data. Experimental results on two benchmark gait databases, CASIA gait database and the challenge USF gait database, demonstrate the effectiveness of the proposed method. HighlightsWe overcome the shortcomings of CCA when dealing with high-dimensional matrix.The singularity of generalized eigenvalue problem in CCA is overcome naturally.The important discriminative information is preserved completely in our algorithm.Our scheme learns stable and complete solutions.The multi-view gait recognition is achieved based on our method.

Class Energy Image Analysis for Video Sensor-Based Gait Recognition: A Review

Gait is a unique perceptible biometric feature at larger distances, and the gait representation approach plays a key role in a video sensor-based gait recognition system. Class Energy Image is one of the most important gait representation methods based on appearance, which has received lots of attentions. In this paper, we reviewed the expressions and meanings of various Class Energy Image approaches, and analyzed the information in the Class Energy Images. Furthermore, the effectiveness and robustness of these approaches were compared on the benchmark gait databases. We outlined the research challenges and provided promising future directions for the field. To the best of our knowledge, this is the first review that focuses on Class Energy Image. It can provide a useful reference in the literature of video sensor-based gait representation approach.

Fusion of Gait and Facial Features using Coupled Projections for People Identification at a Distance

A novel feature-level fusion scheme for people identification at a distance has been developed by coupling gait feature with facial feature. The proposed coupled projections based method first maps the heterogeneous features from gait and face into a unified subspace to minimize the distance between the two features extracted from the same individual. The fusion features are obtained by computing the mean of the two projecting features from the same person in the coupled subspace. Experimental results demonstrate that the proposed feature-level fusion scheme outperforms the match score-level and two other feature-level fusion schemes in the application of access control at a distance.

Fusion of Local Manifold Learning Methods

Different local manifold learning methods are developed based on different geometric intuitions and each method only learns partial information of the true geometric structure of the underlying manifold. In this letter, we introduce a novel method to fuse the geometric information learned from local manifold learning algorithms to discover the underlying manifold structure more faithfully. We first use local tangent coordinates to compute the local objects from different local algorithms, then utilize the selection matrix to connect the local objects with a global functional and finally develop an alternating optimization-based algorithm to discover the low-dimensional embedding. Experiments on synthetic as well as real datasets demonstrate the effectiveness of our proposed method.

Robust Hessian Locally Linear Embedding Techniques for High-Dimensional Data

Recently manifold learning has received extensive interest in the community of pattern recognition. Despite their appealing properties, most manifold learning algorithms are not robust in practical applications. In this paper, we address this problem in the context of the Hessian locally linear embedding (HLLE) algorithm and propose a more robust method, called RHLLE, which aims to be robust against both outliers and noise in the data. Specifically, we first propose a fast outlier detection method for high-dimensional datasets. Then, we employ a local smoothing method to reduce noise. Furthermore, we reformulate the original HLLE algorithm by using the truncation function from differentiable manifolds. In the reformulated framework, we explicitly introduce a weighted global functional to further reduce the undesirable effect of outliers and noise on the embedding result. Experiments on synthetic as well as real datasets demonstrate the effectiveness of our proposed algorithm.

Erratum: Couple Metric Learning Based on Separable Criteria with Its Application in Cross-View Gait Recognition

Gait is an important biometric feature to identify a person at a distance. However, the performance of the traditional gait recognition methods may degenerate when the viewing angle is changed. This is because the viewing angle of the probe data may not be the same as the viewing angle under which the gait signature database is generated. In this paper, we introduce the separable criteria into the couple metric learning (CML) method, and apply this novel method to normalize gait features from various viewing angles into a couple feature spaces. Then, the gait similarity measurement is conducted in this common feature space. We incorporate the label information into the separable criteria to improve the performance of the traditional CML method. Experiments are performed on the benchmark gait database. The results demonstrate the efficiency of our method.

A New ROI Extraction Method of Non-contact Finger Vein Images

This paper proposes a new rotation correction based method to extract regions of interest (ROI) from non-contact finger vein images. Firstly, finger median lines and image center points are used to make rotation correction. Then the arc diameter of fingertips is introduced to locate and determine sizes of ROI .Finally, do the size normalization. It is proved by experiments that the algorithm can effectively eliminate the finger vein image rotation and translation to some extent, and it is still efficient when the light is uneven to a certain degree or images are not clear enough. That is to say, this algorithm has high accuracy and is robust at the same time.

A Novel Coupled Metric Learning Method and Its Application in Degraded Face Recognition

The coupled metric learning is a novel metric method to solve the matching problem of the elements in different data sets. In this paper, we improved the supervised locality preserving projection algorithm, and added within-class and between-class information of this algorithm to coupled metric learning, so a novel coupled metric learning method is proposed. This method can effectively extract the nonlinear feature information, and the operation is simple. The experiments based on two face databases are performed. The results show that, the proposed method can get higher recognition rate in low-resolution and fuzzy face recognition, and can reduce the computing time; it is an effective metric method.

Research on Finger Vein Recognition Based on NSST

In the finger vein image collection procedure, there are always two kinds of negative factors: the first is unstable illumination, the second is information loss caused by bad collection operation. There are not yet special methods for the above-mentioned question for now. We adopt the Non-Subsampled Shearlet Transform (NSST) coefficients for feature extraction, since the NSST transform domain coefficients are affected less by unstable illumination. For the question of information loss, we first introduce an improved ROI extraction method for database extension. We further propose an improved robust regression classification method for vein recognition. The experimental results show that: compared with traditional methods, our proposed method based on NSST does better in recognizing finger vein images which lack some information and are influenced by the unstable illumination.

A Novel Feature Fusion Scheme for Human Recognition at a Distance

Human identification at a distance remains a challenging problem. Two biometric sources that are available in such situations are gait and face. In this paper, we present a new approach that utilizes and integrates information from frontal gait and face at the feature level. A novel kernel coupled mapping method is introduced to project both the gait features and the face features into a unified subspace where the heterogeneous modalities are transformed into the homologous features naturally. Moreover, the proposed feature level fusion scheme is compared with the match score level fusion schemes (Sum, Max and Product rules) and two feature level fusion schemes. The experimental results demonstrate that the proposed feature level fusion scheme outperforms the match score level and the other two feature level fusion schemes.