Multi - Biometrics Approach for Facial Recognition
C. Nandini, Caroline Nirmala Ravikumar · 2007
The automatic recognition of human faces presents a significant challenge to the pattern recognition research community. Typically, human faces are very similar in structure with minor differences from person to person. Input represents a set of measurements called the pattern vector. Principal component analysis (PCA) approaches to face recognition are data dependent and computationally expensive. To classify unknown faces they need to match the nearest neighbor in the stored database of extracted face features. Pattern recognition system performs a classification function on its input. Input represents a set of measurements called the pattern vector. In this paper we are interested in (1) testing facial performance with the Shannon entropy to the 2D face image, (2) testing 2D face using edge images, called edge based 2D facial recognition, (3) recognizing the person based on 2D Shannon entropy and edge Image data. The proposed approach is tested on the ORLface data sets.