Multi-view face detection and recognition under variable lighting using fuzzy logic

This paper presents a novel approach for detection and recognition of multi-view faces whose size and location is unknown and the illumination conditions are varying. The illumination is a big problem in face detection and recognition. In this paper, a new pre-processing method is proposed in order to cancel the effect of various illumination conditions on a face. Then, a binary face is obtained that its pixels are 0 or 1. Next, a fuzzy face model is produced from the distribution of zeros in the binary face. The model is used in order to detect faces in images by using a fuzzy approach. Because of the independency of the detection method to the skin color of face, persons with every kind of skin color can be detected. Next, the detected face is recognized. Our proposed face recognition method is based on Support Vector Machines, face edges extraction and the eigenface method. The illumination dependency problem of the eigenface method has also been solved by a new method.