Research Of Face Detection Technology Based On Skin Color And Non-negative Matrix Factorization

Face detecting is one of the import techniques used in automatic processing by computer which is about the human face information contained in the digital images. The target is to find out whether there are human faces in digital images. If there are some then return their locations. Human face detecting technique has gained extensive application in many fields such as human face identification, crowd control, intelligent user interface, content based image search, image compress coding and so on.In this paper we studied and compared general face detecting algorithms. In allusion to the characteristics that image of video sequences has low resolution ratio and large quantity of color information; we propose a face detecting method based on skin color and local human face structural feature. First, take pretreatment for the digital images to be detected. We use skin color as condition to search the regions that like to be human skin in the images. Secondly, we utilize the NMF (Non-negative Matrix Factorization) algorithm to extract human face local feature subspace. At last, we trained the SVM (Support Vector Machine) with the power value vectors which the training examples project on the face features subspace. After this training process we use the SVM obtained to classify face regions and non-face regions. In this...