Hits:

Indexed by:会议论文

Date of Publication:2008-01-01

Included Journals:CPCI-S

Page Number:803-+

Key Words:face detection; Gaussian distribution; projection; skin model

Abstract:The speed and the accuracy of face detection algorithm are very important for network sensors applied in human-computer-interface. A new method of face detection is presented in this paper. The algorithm is based on skin color clustering features and projecting distribution characteristic. Firstly, the approach utilizes the skin color features to transform the original image into a binary-image. Then projecting the binary-image to X-axes and Y-axes respectively, two curves are obtained. Their means and variances can be obtained. Gaussian distribution curves with same means and variances can be calculated. Finally, according to the solution of Gaussian equation, an accurate face region is found. Simulation shows that the method proposed is fast and needs less computation.