Research on face detection and recognition aims at enabling machines to possess face recognition ability similar to that of human beings.It has essential applications in the domain of personal identification,human-computer interface,image retrieval, visual surveillance,etc.Although the topic has received much attention in pattem recognition and computer vision community, many open problems remain to be resoled.In this thesis,we describe several novel algorithms in an attempt to solve some of the problems.The contributions of the thesis include: (1)An elaborate comparative study on various color representation schemes for skin detection has been performed.The comparative results are expected to be of great value for related research.A novel adaptive skin region detection algorithm is proposed based on a non-parametric fuzzy skin color model.Based on the complementarity of the information between positive and negative samples,it provides an improved realization for skin region detection under unconstrained conditions. (2)A novel face detection algorithm is proposed through fusion of multi-cues.It combines skin color, face contour and face region information,Fusion of multi-cues is in accordance with the mechanisms of biological vision.An effective form of feature extraction is proposed to represent the face contour pattern.Experimental results show the robustness and accuracy of the proposed method. (3)A face verification scheme based on personalized feature combination is proposed and realized.The algorithm is inspired by the adaptation mechanism of the human visual system in face recognition.We simulate such mechanism through personalized fusion of global and local facial features.Experimental results demonstrate the necessity of personalized data fusion for face recognition and illustrate the effectiveness of the proposed algorithm.
修改评论