Neuro Fuzzy Network and Wavelet Gabor For Face Detection


This paper presents a face detection technique based on two techniques: wavelet Gabor filter for extract features from the localized facial image and neuro fuzzy system used as classifier depending on the features that extract , where it is used to determine the faces in the input image by draw boxes around the faces. The neurofuzzy network will be train on 128 image (69 face and 59 non face, size of each image 16*27 pixel in gray scale , this mean it trained to choose between two classes “face” and “non-face” images. Our approach has been tested on eight common images with different face number in image and different number of fuzzy set. We got the best detection rate is 89.3% in case threshold equal 0.2 and in case number of fuzzy set equal 2. The stages of this work are implemented in MATLAB 7.0 environment.