Yufei Han

Learning Gabor magnitude features for palmprint recognition

Palmprint recognition, as a new branch of biometric technology, has attracted much attention in recent years. Various palmprint representations have been proposed for recognition. Gabor feature has been recognized as one of the most effective representations for palmprint recognition, where Gabor phase and orientation feature representations are extensively studied. In this paper, we explore a novel Gabor magnitude feature-based method for palmprint recognition. The novelties are as follows: First, we propose an illumination normalization method for palmprint images to decrease the influence of illumination variations caused by different sensors and lighting conditions. Second, we propose to use Gabor magnitude features for palmprint representation. Third, we utilize AdaBoost learning to extract most effective features and apply Local Discriminant Analysis (LDA) to reduce the dimension further for palmprint recognition. Experimental results on three large palmprint databases demonstrate the effectiveness of proposed method. Compared with state-of-the-art Gabor-based methods, our method achieves higher accuracy.

Palmprint recognition under unconstrained scenes

This paper presents a novel real-time palmprint recognition system for cooperative user applications. This system is the first one achieving noncontact capturing and recognizing palmprint images under unconstrained scenes. Its novelties can be described in two aspects. The first is a novel design of image capturing device. The hardware can reduce influences of background objects and segment out hand regions efficiently. The second is a process of automatic hand detection and fast palmprint alignment, which aims to obtain normalized palmprint images for subsequent feature extraction. The palmprint recognition algorithm used in the system is based on accurate ordinal palmprint representation. By integrating power of the novel imaging device, the palmprint preprocessing approach and the palmprint recognition engine, the proposed system provides a friendly user interface and achieves a good performance under unconstrained scenes simultaneously.

Palmprint recognition based on directional features and graph matching

Palmprint recognition, as a reliable personal identity check method, has been receiving increasing attention during recent years. According to previous work, local texture analysis supplies the most promising framework for palmprint image representation. In this paper, we propose a novel palmprint recognition method by combining statistical texture descriptions of local image regions and their spatial relations. In our method, for each image block, a spatial enhanced histogram of gradient directions is used to represent discriminative texture features. Furthermore, we measure similarity between two palmprint images using a simple graph matching scheme, making use of structural information. Experimental results on two large palmprint databases demonstrate the effectiveness of the proposed approach.

Fusion of Face and Palmprint for Personal Identification Based on Ordinal Features

In this paper, we present a face and palmprint multimodal biometric identification method and system to improve the identification performance. Effective classifiers based on ordinal features are constructed for faces and palmprints, respectively. Then, the matching scores from the two classifiers are combined using several fusion strategies. Experimental results on a middle-scale data set have demonstrated the effectiveness of the proposed system.

Palmprint image synthesis: A preliminary study

In this paper we present a preliminary study of palmprint image synthesis and propose a framework for synthesizing palmprint texture. We first extract principal lines of real palm- prints using edge detection and synthesize wrinkles and ridges of palm using patch-based sampling. Then we incorporate principal lines, wrinkles and ridges to obtain the final synthetic image. After that multiple images are derived from each artificial palm to simulate the intra-class images. Our approach can generate large palmprint databases which preserve inter-class and intra-class variations. Experimental results demonstrate that the synthetic images bear a close resemblance to real palmprints in terms of appearance as well as statistical properties, showing a promising usage in algorithms evaluation and comparison.

Combine hierarchical appearance statistics for accurate palmprint recognition

Palmprint recognition is an active member of biometrics in recent years. State-of-the-art algorithms of palmprint recognition describe appearances of palmprints efficiently through local texture analysis. Following this framework, we propose a novel approach of palmprint recognition in this paper, which represents palmprint images based on statistics and spatial arrangement of appearance descriptors within local image areas. In this method, we firstly design a robust descriptor to encode properties of palmprint appearances of local regions. The whole image is divided into non-overlapped blocks at increasingly fine resolutions successively, so as to describe the spatial layout in hierarchical scales. For a specific spatial resolution, local distributions of the proposed descriptors in the blocks are concatenated to represent structures of palmprint structures. Finally, distribution information of different resolutions is combined to provide complementary descriptive power. Promising experimental results demonstrate that the proposed method achieves even better performances than the state-of-the-art approaches.

Palmprint Recognition Based on Regional Rank Correlation of Directional Features

Automatic personal identification based on palmprints has been considered as a promising technology in biometrics family during recent years. In pursuit of accurate palmprint recognition approaches, it is a key issue to design proper image representation to describe skin textures in palm regions. According to previous achievements, directional texture measurement provides a powerful tool for depicting palmprint appearances. Most of successful approaches can be ranged into this framework. Following this idea, we propose a novel palmprint representation in this paper, which describes palmprint images by constructing rank correlation statistics of appearance patterns within local image areas. Promising experimental results on two large scale palmprint databases demonstrate that the proposed method achieves even better performances than the state-of-the-art approaches.

Accurate Palmprint Recognition Using Spatial Bags of Local Layered Descriptors

State-of-the-art palmprint recognition algorithms achieve high accuracy based on component based texture analysis. However, they are still sensitive to local variations of appearances introduced by deformation of skin surfaces or local contrast variations. To tackle this problem, this paper presents a novel palmprint representation named Spatial Bags of Local Layered Descriptors (SBLLD). This technique works by partitioning the whole palmprint image into sub-regions and describing distributions of layered palmprint descriptors inside each sub-region. Through the procedure of partitioning and disordering, local statistical palmprint descriptions and spatial information of palmprint patterns are integrated to achieve accurate image description. Furthermore, to remove irrelevant and attributes from the proposed feature representation, we apply a simple but efficient ranking based feature selection procedure to construct compact and descriptive statistical palmprint representation, which improves classification ability of the proposed method in a further step. Our idea is verified through verification test on large-scale PolyU Palmprint Database Version 2.0. Extensive experimental results testify efficiency of our proposed palmprint representation.

Palmprint recognition using coarse-to-fine statistical image representation

Recent literatures have revealed that statistics of local texture measures can provide accurate descriptions of palmprint appearances. In this framework, one palmprint image is divided into local blocks with multiple spatial resolutions. The statistical texture descriptions of each block are then concatenated to form a multi-scale image representation. However, resultant high-dimensional statistical features lead to increasing of computational cost. In this paper, we tackle this problem by performing a coarse-to-fine cascade scheme, which makes use of information redundancy of statistical texture descriptions between different spatial scales. In contrast with non-cascade strategies, the proposed method reduces most of computational burden and achieves accurate classification simultaneously.