Face Detection Method Based On Skin Color Segmentation Pretreatment Study

Images containing faces are essential to intelligent vision-based human computer interaction, and research efforts in face processing include face recognition, face tracking, pose estimation, and expression recognition. However, all of these researching directions involve in one problem-face detection and location. In other words, before this face processing, we must know faces' locations and scales. Consequently, to build an automated face processing system which analyzes the information contained in face images, robust and efficient face detection algorithms are required.The research on face detection has lasted for more than twenty years. But, up to now, due to the complexity of the purpose such as the diversity of face patterns, variable lighting condition and so on, many researches can not resolve the problem completely even if they have studied it for long time. In this thesis, the author has done some work on the face detection.The work includes: (1) A skin color segmenting approach based on YCbCr color space.Among many color spaces, this paper used YCbCr components. Since in the YCbCr color space, the luminance information is contained in Y component; and the chrominance information is in Cb and Cr. Therefore, the luminance information can be easily de-embedded.Applied this approach to the pre-processing of the face detection system, it can discard background regions of the image quickly while spend more computation on promising face-like regions, so enhance the executing efficiency and detecting performance of the face detection system.(2) A face detector based on skin color segmenting pre-processing and template-matching.The face detection approach based on template matching has the advantage of being simple to implement, and achieves a stable and dependable performance in upright face detection application. However, it has proven to be inadequate for face detection since it cannot effectively deal with variation in scale, pose and shape, and it has a higher computation cost. At the same time, the approach based on skin color has a less computation cost, but its performance is unstable. So we integrate the both and propose a new face detector based on skin color segmenting pre-processing and template matching.In order to save the time to magnify or shrink a face template to meet the size of the test image, a group of face templates was stored in a database so that an appropriate face template can be called with ease without going through image enlarging or shrinking process.The results of experiments show this method of face detection achieves a higher executing efficiency and fewer false detects.(3) A face detector based on skin color segmenting pre-processing and neural network validation.Neural networks have been applied successfully in face detection problem. The advantage of using neural networks for face detection is the feasibility of training a system to capture the complex class conditional density of face patterns. However, one drawback is that it need apply an exhaustive window scanning technique to input image for possible face locations at all scales. This reduces the executing efficiency of the detector in great extent and restricts it to apply to some real-time face detection application.Based the MLP detector proposed by D. Anifantis etc., the author present a restricted window scanning strategy that is scanning in candidate face regions which created by the skin color segment preprocess, and built a new face detector.The results of experiments show the new face detector achieves a higher executing efficiency and fewer false detects than traditional NN detector.