Texture Analytics for Accurate Person Recognition: A Multimodal Approach

Securing the resources is a most challenging task in digital era. Traditionally, password and ID card systems were used to provide security. Password cards can be stolen or hacked; overcome this drawback biometric are authenticate user access data resources. Biometric system uses physical behavioral characteristics of user. Biological person like face, fingerprint, iris, palm print, voice, hand geometry etc. cannot misused. Even though unimodal more secure as compared traditional approach, it not able handle intra-class, inter-class variations, noisy spoofing attack. These problems solved using multimodal biometrics. In paper, we discuss Local Binary Pattern (LBP) Ternary (LTP). We propose feature level fusion face fingerprint traits LTP. The implementation introduced stands comparison LBP LTP for system. tested on ORL, UMIST, VISA dataset FVC dataset. Experimental results show that gives better accuracy