| Face detection is original from face recognition, which is the key section of face recognition system. In recent years, face detection has been attached importance to by researchers as an absolute task with the development of electronic commerce. Nowadays, the application background of face detection has exceeded the range of face recognition system, and it has important applied value in Content-Based Image Retrieval, Digital Video Processing and Visual Supervision And Control etc.This paper has studied mainly and further faces detection technology. At first we have studied the face detection algorithm based on skin mode and gradient geometry, and imported fractal theory into face detection, then presents a new face detection method—face detection based on fractal texture and Cascade classifier.On studying the face detection algorithm based on skin mode and gradient geometry, we analysis the existing method and present betterment on the choice of threshold of skin mode and the searching face on grads geometry. Experiment result indicates the method can be adapted to face detection in normal color image.At last, this paper emphasis on the discussing and studying of the application which fractal theory is in face detection. We present a presents a new face detection method—face detection based on fractal texture and Cascade. This is the first time to import fractal theory into face detection. Face includes abundant textures, and face puts up jagged and irregular shape which has self-similarity between them. That shows face image bear fracture feature. This paper obtains the reliability of fracture texture feature in face detection through analyzing and studying in fractal texture feature parameters (box-dimension, difference fractal dimension, lacunarity) of face and nonface image. Then gains strong classifier which can classify face and non-face, based on fracture texture feature and training of cascade classifier. Experimental results show that this method is effective and workable.
|
PDF Full Text Request