Jian-Ping Li

Multibiometric Cryptosystem: Model Structure and Performance Analysis

Single biometric cryptosystems were developed to obtain win-win scenarios for security and privacy. They are seriously threatened by spoof attacks, in which a forged biometric copy or artificially recreated biometric data of a legitimate user may be used to spoof a system. Meanwhile, feature alignment and quantization greatly degrade the accuracy of single biometric cryptosystems. In this paper, by trying to bind multiple biometrics to cryptography, a cryptosystem named multibiometric cryptosystem (MBC), is demonstrated from the theoretical point of view. First, an MBC with two fusion levels: fusion at the biometric level, and fusion at the cryptographic level, is formally defined. Then four models, namely biometric fusion model, MN-split model, nonsplit model, and package model, adopted at those two levels for fusion are presented. Shannon entropy analysis shows that even if the biometric ciphertexts and some biometric traits are disclosed, the new constructions still can achieve consistently data security and biometric privacy. In addition, the achievable accuracy is analyzed in terms of false acceptance rate/false rejection rate at each model. Finally, a comparison on the relative advantages and disadvantages of the proposed models is discussed.

A Novel Authentication Scheme of the DRM System based on Multimodal Biometric Verification and Watermarking Technique

Digital Rights Management (DRM) system is the effective schemes for digital transactions. A novel authentication scheme of the DRM system based on multimodal biometric verification and watermarking technique is described in this paper, which is based on highly secure iris recognition and face recognition and their feature fusion recognition is described, which is can achieve the rights management of digital content exactly through the illegal user access control. In watermarking algorithm, face image is chosen to be the host image. Iris feature is selected to use as watermark hidden in the host image. Such that iris feature watermark not only protects face biometric data, but also can be used as a covert recognition. Meanwhile, the bimodal biometrics recognition provides the improvement in the accuracy performance of the system.

Data Classification based on Artificial Neural Networks

Data classification has been studied widely in the fields of Artificial Intelligence, Machine Learning, Data Mining and Pattern Recognition. Up to the present, the development of classification has made great achievements, and many kinds of classified technology and theory will continue to emerge. This paper discusses a great deal of classification algorithms based on the Artificial Neural Networks, such as the perceptron, back propagation network and probabilistic neural networks. According to analysis these classification, we mainly concern these strengths and weaknesses and performance.

A new fingerprint-based remote user authentication scheme using mobile devices

Recently, Khan et al. proposed an efficient and practical chaotic hash-based fingerprint biometric remote user authentication scheme on mobile devices. Unfortunately, Yoon-Yoo demonstrated that Khan et al.s scheme was vulnerable to a privileged insider attack and an impersonation attack by using lost or stolen mobile devices. To isolate such problems, Yoon-Yoo proposed an improvement to Khan et al.s scheme. However, the two authentication schemes required synchronized clocks between the user and the remote system server because of using timestamps in authentication process. Actually, it is fairly complicated to achieve time concurrency mechanism; and network environment and transmission delay is unpredictable, so some drawbacks exist in their scheme. To overcome those weaknesses, a new fingerprint-based remote user authentication scheme using mobile devices is proposed. The proposed scheme can safely achieve mutual authentication between the users and the remote system. Compared with other related schemes, the proposed scheme not only is secure and efficient but also can provide good characteristics. Hence, our proposed scheme can be easily realized in the practical environment.

Robust person identification with face and iris by modified PUM method

In previous works, we have applied the modified PUM method in face recognition and demonstrated the effectiveness of this method for deal with partial occlusion and distortion. Based on the similitude between the face features and iris features, this paper proposes a new method for person recognition by the combining of iris and face. This new method combines the iris and face features as a new feature for representing persons and then acts the modified PUM on the new features for recognition. Generally, the iris features, however, is more reliable than the face features. Hence the iris feature should be given a higher weight. For this, this paper further improves the method to form a better strategy for combining the face and iris on recognition. The new improved approach has been evaluated on combined-face and iris databases, using face testing images subjected to various types of partial distortion and occlusion. The new system has demonstrated improved performance over other systems.

Research on data fusion of multiple biometric features

Given uncertain status reports or notes come from multi-sensor, identity fusion further makes them integrate information and jointly determine the observed entities. This paper discusses an improved data fusion approach to multi-biometric feature, including face, fingerprint and iris image. The approach is called improved multiple biometric data fusion algorithm, based on the eigen-face and the Gabor wavelet methods, incorporating the advantages of the single algorithm. Now we have built a new fusion system, which has demonstrated the improved performance over single biometric systems.

A new method of iris image location research

At present, the research of biometric recognition is gave more and more attention in the world. The iris recognition is a kind of the biometrics technologies based on the physiological characteristics of human body, compared with the feature recognition based on the fingerprint, palm-print, face and sound etc. the iris recognition technology has recently become popular in identity recognition. In my paper, based on the existing iris location algorithm, an improved iris location algorithm is brought forward. This method can achieve a precise and rapid iris location. In this method, inner circle positioning algorithm is improved by the changed Ostu adaptive binarization thresholding algorithm and the changed gray-scale projection method. And external positioning is completed by Roberts operator.

The Contourlet Transfrom and SVM Classification for Face Recognition

In this paper, we introduce a face recognition approach based on the contourlet transform and support vector machine, which takes technological advantages of both support vector machine and the contourlet transform for feature extraction. The contributions of this paper include the following aspects: (1) support vector machine is successfully applied to face recognition by using the contourlet transform as the face representation in face image processing phase; (2) the contourlet transform are used to represent a whole face in a computable dimensional space. The new method was evaluated with many experiments, and the experimental results show that our face recognition algorithm is effective and competitive.

Application of Wavelets Analysis in Image Denoising

Aiming at the problems of images denoising, wavelet algorithm is introduced simply. The technology of images denoising based on wavelet are analyzed in detail. Image denoising is achieved by Matlab. Two thresholding in the process of image denoising are compared by the results of experiments. Meanwhile, the advantages of image denoising by wavelet is proved.

Face recognition using illumination invariant features in contourlet domain

This paper summarizes the recent development of illumination compensation for face recognition. Then a new method is proposed by extracting illumination invariant features in contourlet transform domain based on human visual perception mechanism. The experimental results on Yale B and CMU PIE face databases demonstrate that it is effective and competitive.