No abstract

Face detection is integral to any automatic face recognition system. The goal of this research is to develop a system that performs the task of human face detection automatically in a scene. A system to correctly locate and identify human faces will find several applications, some examples are criminal identification and authentication in secure systems. This work presents a new approach based on principal component analysis. Face silhouettes instead of intensity images are used for this research. It results in reduction in both space and processing time. A set of basis face silhouettes are obtained using principal component analysis. These are then used with a Hough-like technique to detect faces. The results show that the approach is robust, accurate and reasonably fast.

The classical Hough transform, the generalized Hough transforms, and their extensions are quite robust for detection of a large class of objects that can be categorized as industrial parts. These objects are rigid and have fixed shapes, i.e., different instances of the same object are more or less identical. These techniques, and indeed most current techniques, however, do not adequately handle shapes that are more flexible. These shapes are widely found in nature and are characterizedby the fact that different instances of the same shape are similar, but not identical, e.g., leaves and flowers. We present a new technique to recognize natural shapes, based on principal component analysis. A set of basis shapes are obtained using principal component analysis. A Houghlike technique is used to detect the basis shapes. The results are then combined to locate the shape in the image. Experimental resuits show that the approach is robust, accurate, and fast.