Automatic Face and Facial Features Detection

초록

Many researches have been presented to search face region for human recognition and coding schemes. In this paper, we propose an automatic face and facial features detection algorithm. There are two main steps; the face region detection from original complex image, and the facial feature extraction from the detected face region. Genetic Algorithm(GA) is used to search face region in background for the first step. For the facial feature, we propose two methods; one of them is a geometric method using people’s face information and the other is the method using a Gaussian Derivatives Filters. We can get a good experimental result for face detection, and that is irrespective of the image size, wearing the glasses and mustache. For the two methods of detecting facial feature, the method using geometric property is faster than a Gaussian Derivatives Filters, but the former is less exact than the latter.