Research And Application In Video Of The Face Detection Arithmetic

Further and sufficient discussions on algorithm of video object segmentation are presented in this dissertation in aspect of single frame segmentation and multi-frame difference segmentation, on base of which, the quick face detection and orientation achieve.Firstly, in aspect of spatial segmentation, an improved watershed strategy is presented in image pre-processing and region labeling to restrain over-segmentation in conventional watershed caused by noise and close textures.Secondly, as for motion detection for stationary background sequences, an idea of representing region motion with region's boundary information is created to resolve the problem existing in region-based method. Only through Gaussian test on boundary pixels and motion pixels ratio to whole boundary can motion regions be identified.Thirdly, Markov Random Field model on double scale neighborhood is established for motion detecting of dynamic background sequences. Integrating gauss mixture distribution with MRF on difference images, a motion detecting model and convenient system energy function are proposed.Finally, on base of the eyes detection and orientation within the candidate region, face can be detected and orientated quickly by geometrical characteristic and gray scale.