Multimodal Biometric Human Face Authentication System using Text Dependent Speech Signal

Abstract

Multimodal biometric face recognition using speech signal has engrossed much attention and has been applied in various domains. In recent years much advancement have been made in face recognition techniques to cater to the challenges such as pose, expression, illumination, aging and disguise. A fundamental challenge in face recognition lies in determining which facial characteristics are important in the identification of faces. However, due to advances in technology, there are new emerging challenges for which the performance of face recognition systems degrades and plastic/cosmetic surgery is one of them. Face-recognition algorithms have been battling the effects of awkward poses, facial expressions, and disguises like hats, wigs, and fake moustaches. They had some success, but they may be meeting their match in plastic surgery. For more global changes like a face-lift, the results were dismal a match rate of just 2 percent. But even after plastic surgery, there are some features beneath the skin will still observable that remains unchanged for a long time. In this paper we comment on the effect of plastic surgery face image in multimodal biometric face recognition using speech signal. Speaker identity is correlated with the physiological and behavioral characteristics of the speaker. These characteristics exist both in the spectral envelope (vocal tract characteristics) and in the supra-segmental features (voice source characteristics and dynamic features spanning several segments). Selecting the most effective fusion techniques depends on operational issues such as accuracy requirements, availability of training data, and the validity of simplifying assumptions. Of the techniques evaluated, product of likelihood ratios and logistic regression were found to be highly effective.