Hengxin Chen

Fragmented edge structure coding for Chinese writer identification

As a branch of biometrics, handwriting-based writer identification is an active research topic in pattern recognition. This paper presents a theoretically very simple, yet efficient, multiresolution approach to off-line, text-independent Chinese writer identification based on edge structure code (ESC) distribution feature and nonparametric discrimination of sample. ESC distribution feature is based on probability distribution function, which characterizes the frequent structures distribution of edge fragments on multiple scales. Experiments were conducted on an open HIT-MW database which is widely used for performance evaluation. Experimental results show that the proposed method was able to improve the identification accuracy.

A MULTI-LAYER CONTRAST ANALYSIS METHOD FOR TEXTURE CLASSIFICATION BASED ON LBP

Texture classification is one of the important fields in pattern recognition and machine vision research. LBP method,13–15 proposed by Ojala, can be used to classify texture images effectively. And...

Signature envelope curvature descriptor for offline signature verification

This paper presents an algorithm for feature descriptor extraction of signature using signature envelope curvature sequences which are rotation invariant. The envelope curvature reflects both the direction change pattern of the envelope sequence and smoothness of the envelope that are usually employed for signature verification by human experts. A polygon matching technique is applied to eliminate the shift effect which results from the arbitrary start point selection for calculation of the proposed envelope curvature features. To make the method robust to be size invariant, a normalization process is done with additional benefit of feature dimension reduction. Finally, experimental results show comparable performance of the proposed method aiming at simple and skill forgery detection for offline signature verification.

A FUSION FRAMEWORK FOR FACE RECOGNITION UNDER VARYING ILLUMINATION BASED ON MULTI-SCALE ANALYSIS

Varying illumination is a huge challenge of face recognition. The variation caused by varying illumination in the face appearance can be much larger than the variation caused by personal identity. The high frequency signal component in image represents the detail characteristic of the face, and for the reason of being influenced scarcely by varying illumination, this signal component can be used as illumination invariance features in face recognition. However, the definition of the high frequency signal component is blurry, and it is impossible to separate this component from the face image exactly. Because of using the different decomposition methods and different decomposition parameters, high frequency component has been dispersed in decomposed detail images that characterize themselves by containing different scale frequency signal component. This paper proposes a framework to fuse that high frequency signal components in multi-scale detail images using adaptive weight. This novel framework is an open...

A COMPUTATIONAL AND THEORETICAL ANALYSIS OF LOCAL NULL SPACE DISCRIMINANT METHOD FOR PATTERN CLASSIFICATION

Many problems in pattern classification and feature extraction involve dimensionality reduction as a necessary processing. Traditional manifold learning algorithms, such as ISOMAP, LLE, and Laplacian Eigenmap, seek the low-dimensional manifold in an unsupervised way, while the local discriminant analysis methods identify the underlying supervised submanifold structures. In addition, it has been well-known that the intraclass null subspace contains the most discriminative information if the original data exist in a high-dimensional space. In this paper, we seek for the local null space in accordance with the null space LDA (NLDA) approach and reveal that its computational expense mainly depends on the quantity of connected edges in graphs, which may be still unacceptable if a great deal of samples are involved. To address this limitation, an improved local null space algorithm is proposed to employ the penalty subspace to approximate the local discriminant subspace. Compared with the traditional approach, the proposed method can achieve more efficiency so that the overload problem is avoided, while slight discriminant power is lost theoretically. A comparative study on classification shows that the performance of the approximative algorithm is quite close to the genuine one.

Offline signature verification based on the gabor transform

Research has been active in the field of forgery detection, but relatively little work has been done on the detection of skilled forgeries. This paper presents a new feature extraction method based on the intensity of the coefficients of the Gabor transform. The new method first uses the multichannel Gabor transform, then the transformed image of Gabor was equally divided into some non-overlapping boxes, and the angle features of the position of the maxima intensity of the Gabor transform coefficients were extracted. Experiment results indicate that the proposed method enable to improve verification accuracy.

AN ADAPTIVE FUZZY FUSION FRAMEWORK FOR FACE RECOGNITION UNDER ILLUMINATION VARIATION BASED ON LOCAL MULTIPLE PATTERNS

Local binary pattern (LBP) operator offers an efficient way to recognize face under varying illumination, while it has the drawback of abandoning some important texture features. Local multiple patterns (LMP) has alleviated the problem by a hierarchical model. However, the LMP method can bring out the rapid expansion of feature dimension, so a special feature encoding method is adopted by this paper. Meanwhile, we find that the LMP features of different layers can be used to recognize face independently so that it would preserve more abundant recognition information. Most importantly, the contribution of the LMP features from different layers is blurry under varying illumination. We propose a fuzzy framework to fuse the recognition result of different layers and use adaptive weights to calculate contribution rates of different layers under varying illumination. Experimental results demonstrate that the proposed method outperforms other state-of-the-art methods on four databases such as Yale B, Extended Yale B, CMU PIE and Outdoor.

A glass image classification method based on multi-feature fusion

In this work, a new glass classification method is proposed. Firstly, images are enhanced by image preprocessing. Secondly, a series of glass features including shape and texture features are proposed. Finally, we employ simple minimum distance classifier to classify the input glass images. The experimental results show that the proposed method has high classification efficiency and accuracy.

A method for multiple morph targets tracking based on region growing

It is very important to count passengers who get on and get off for scheduling bus effectively. The tracking methods based on target shape and feature points can not be adopted to this case, because the target shapes keep changing from time to time randomly and even appear partially in field of vision captured. Based on difference image and region growing, a new method is proposed in this paper for tracking the multiple moving targets whose shapes are variable. The result of experiment shows that the method is able to count passengers with preferable accuracy in real-time application.