No abstract

As a novel approach to perform user authentication, we propose a multimodal biometric system that uses faces and gestures obtained from a single vision sensor. Unlike typical multimodal biometric systems using physical information, the proposed system utilizes gesture video signals combined with facial images. Whereas physical information such as face, fingerprints, and iris is fixed and not changeable, behavioral information such as gestures and signatures can be freely changed by the user, similar to a password. Therefore, it can be a countermeasure when the physical information is exposed. We aim to investigate the potential possibility of using gestures as a signal for biometric system and the robustness of the proposed multimodal user authentication system. Through computational experiments on a public database, we confirm that gesture information can help to improve the authentication performance.

Recently multimodal biometrics technology that employs more than two types of biometrics data has been popularly used for person authentication and verification. In particular, the score-level fusion approach which combines matching scores from unimodal systems to make final decision has gained lots of attentions. In most of these works, however, they assume all the matching scores to be of the same quality. This assumption may cause the problem not to reflect such situation that the qualities of the matching scores from certain unimodal systems are relatively low. To deal with this problem, we propose the RBF based score-level fusion approach which incorporates the quality information of the scores in developing classification models. According to our experimental results, the proposed method using quality information showed its superiority in the performance of person authentication to the usual RBF based score-level fusion without using quality information.

No abstract

In the field of visual information processing, there have been active studies on the efficient representation of visual data, such as local feature descriptors and tensor subspace analysis. Though these methods give a representation using matrix features, current methods for classification are mainly designed for 1D vector data, which may lead to loss of information included in 2D matrix data. To solve the problem, we propose a matrix correlation distance for 2D image data by extending the correlation distance for random vectors. Through a number of computational experiments on image data with various representations, we compare the performance of the proposed measure with conventional distances.