Narrow Results

Face recognition received a lot of attention in the recent past. Most of the reported techniques are based on use and analysis of the two-dimensional (2D) information available in the 2D facial images. Since human faces are originally three-dimensional (3D) objects, association of 3D sensed information can make face recognition more robust and accurate. This paper reports a method for recognition of faces by utilizing phase codes obtained from projected structured light patterns onto the faces. The phase differences associated with the distorted projected patterns are detected and the computed phase maps are utilized to synthesize complex signature functions, spatial frequency distributions of which are directly proportional to the computed phase maps and hence to the original 3D face shape. The synthesized signature functions of the test faces are compared with that of the target face by digital cross-correlation. Analyses of the cross-correlation intensities (squared modulus) complete the recognition process. Preliminary experimental results are presented for faces with wide variations of pose (out-of-plane head rotations).

Face recognition is a rapidly growing research area due to it is contactless, most natural and most humanized. Many issues needed to do research exist in face recognition. A novel wavelet-based and SVM framework for face training and recognizing is proposed. FMT and PCA are also used for improving the accuracy and performance. In order for searching for the best performance, many experiments conducted with this method show that face recognition is largely affected by wavelet decomposing level, and at the same time by SVM type and kernel. So for high recognizing accuracy, proper methods and parameters are needed. The results prove that our scheme is an efficient method as 2D facial image recognition.

Cryptographic key is the central problem in cryptographic techniques. The key based on password protection is not enough secure because of the low entropy in user chosen passwords that can be exploited to launch password-guessing attacks. And the length of cryptographic key generated from user's biometric features directly is limited. Differ from prior methods, a novel scheme of cryptographic key generation based on biometric features and secret sharing is proposed. Biometric feature vectors is transformed through orthogonal matrix, and mapped to integer spaces. Then, a steady integer vector is obtained, and can be utilized to bind with cryptographic key by Shamir's secret sharing scheme. This method may realize the security of key storing, and can produce the key of the arbitrary length.

With the development of the technology of information security, iris recognition based on biometrics has become more and more important. In an iris recognition system, preprocessing, especially iris localization plays a very important role. So far, there are many iris localization algorithms having been proposed. In this paper, we propose an iris localization algorithm, in which we localize iris through detecting the edge points and improved integral differential operator and curve fitting. All the procedures of the algorithm are proved to be valid through our experiment on 648 iris images from CASIA (The Institute of Automation, Chinese Academy of Sciences) database.

Visual recognition of faces is an essential behavior of humans: we have optimal performance in everyday life and just such a performance makes us able to establish the continuity of actors in our social life and to quickly identify and categorize people. This remarkable ability justifies the general interest in face recognition of researchers belonging to different fields and specially of designers of biometrical identification systems able to recognize the features of person's faces in a background.

Due to interdisciplinary nature of this topic in this contribute we deal with face recognition through a comprehensive approach with the purpose to reproduce some features of human performance, as evidenced by studies in psychophysics and neuroscience, relevant to face recognition. This approach views face recognition as an emergent phenomenon resulting from the nonlinear interaction of a number of different features. For this reason our model of face recognition has been based on a computational system implemented through an artificial neural network.

This synergy between neuroscience and engineering efforts allowed us to implement a model that had a biological plausibility, performed the same tasks as human subjects, and gave a possible account of human face perception and recognition. In this regard the paper reports on an experimental study of performance of a SOM-based neural network in a face recognition task, with reference both to the ability to learn to discriminate different faces, and to the ability to recognize a face already encountered in training phase, when presented in a pose or with an expression differing from the one present in the training context.

User always needs to remember passwords in many systems. But a low-entropy password is easy to be attacked, and a high-entropy password is not easy to be remembered. A scheme of key generation from face features is proposed. This scheme is based on FCS (Fuzzy Commitment Scheme) and utilizes the error-correct encoding technique and Hash algorithm to hide random key into biometric features. It realized secure key reconstruction and authentication. This scheme not only protects the user's key but also prevents user's biometric features revealed effectively. The design is provably effective for biometric key generation and secure management through the experiment. The scheme is easy to extend to other biometrics since the extracting process of biometric features can not affect it.