Combining Rectangular and Triangular Image Regions to Perform Real-Time Face Detection
作者单位:Dep.of Computer ScienceSoft Computing and Image Analysis Group IT-Networks and Multimedia Group Universidade da Beira InteriorCovilhPortugal
会议名称:《2008 9th International Conference on Signal Processing(ICSP’2008)》
会议日期:2008年
学科分类:08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程]
关 键 词:Face Detection Feature Extraction Object Detection
摘 要:Nowadays,face detection techniques assume growing relevance in a wide range of applications(e.g.,biometrics and automatic surveillance)and constitute a prerequisite of many image processing *** a large number of published approaches,one of the most relevant is the method proposed by Viola and Jones [18] to perform real-time face detection through a cascade schema of weak classifiers that act together to compose a strong and robust *** method was the basis of our work and motivated the key contributions given in this *** first,based on the computer graphics concept of triangle mesh we propose the notion of triangular integral feature to describe and model face ***,we show results of our face detection experiments that point to an increase of the detection accuracy when the triangular features are mixed with the rectangular in the candidate feature set,which is considered an ***,it should be stressed that this optimization is obtained without any relevant increase in the computational requirements,either spacial or temporal,of the detection method.