Computer vision based face detection and matching is playing an important role in our life. It is allowing future human computer interface to be more intuitive and user-friendly than traditional interfaces. This paper presents a proposed approach to detect a human face dependent on a skin color and matching it with about 100 other human faces by using wavelet function transform. Different physical shapes of faces, face expression such as smiling, laughing, faces having glasses, rotation, and gender of faces (man or woman), can be detected and matched with the same face in different reaction in another image based on the proposed approach. In this approach we achieve approximately 95% for human face detection, and 93% for face matching.

Keywords:

Human Face Detection, Face Matching, Standard Deviation, Wavelet Transform

1Math Dept. Faculty of Science, Helwan university, Cairo, Egypt.

2Electronic Research Institute, Cairo, Egypt.