Multimodal Biometric Authentication System Using Face and Voice Features

Abstract

From past several years, interest towards theories & algorithms of voice and face identification is indeed rapidly evolving. Criminal identification, surveillance of video, unmanned and autonomous vehicles, and building access control are some of the examples for specific technologies which is winning excitement with the industry sectors. Numerous strategies are established, that provides a description of face image by making use of very few whole facial features or face images features. In this research paper, numerous strategies for face and voice detection is being discussed. The ORL is the database used for face recognition. The evaluation process is carried out on an intangible dataset and comprises of ORL image data base for the face. The MFCC voice recognition strategy is addressed by recognizing some of the vibrant speech data sets available.