Implement Of Face Detection And Study Of Eye Location

As the highly development of intelligence technology,more and more researchers and manufacturers have paid attention to the auto identify technology.Especially,with high significant theoretic values,the face recognition technology is important for different human identify.And with wide-potential applications,it is the key point for man-machine interface,video conference and Supervisory system.As the first part of face recognition,an effective face detection method is critical for recognition.As the development of electronic commerce,face detection shows its potential for digital video process,and search based on content area etc.In this paper,we start from face detection based on AdaBoost,and added by optimize module to improve the detection rate.For getting standard face image,we use eye location to normalize face image.Then we developed an integrate face detection system with high practicability.First,the paper analyzes the training and detection process deeply.As the false positive rate is so high after AdaBoost detection,a skin detection module based on the YCrCb color space is analyzed and added to improve the performance of the system.Then,we introduce an effective algorithm based on blocks(BoB) for eye location. The image is partitioned to blocks by a threshold.Based on the comparability between two eyes and the uniqueness of a pair of eyes,it can locate eyes after matching each two blocks.Due to what we use are the location and the comparability between two eyes and eyes are considered in pairs,the algorithm could work on rotated images and get higher detection rate.What's more,it,combined with the circle-feature method, can deal with moderate illumination and expression changes.Experiments on lots of face images have shown that our algorithm is reliable and fast.At last,the system can offer standard face detection result,which is convenient for further process,such as face recognition.