Human Recognition Based On Head-Shoulder Moment Feature
Aimed at the shortcomings of the traditional visual surveillance system,the automatic detection and recognition algorithm of human are studied in Intelligent Monitoring System.This paper uses the moment eigenvector of head-shoulders contour as the back-propagation (BP) neural networks input for human identification by building the 2D model of human head-shoulder.Because of adopting the partial contour shape of the human rather than whole features,it has a better classification on solving the issue of the loss of property arising from human occluded easily in practical applications.At the same time,the mapping relation of feature-class is established by error back-propagation neural network classifier,which completes identification of human.The experiments result shows that this method is effective,and it has strong robustness.
human recognition object abstraction invariant moment back-propagation neural network
Yifang Mao Xiangnian Huang Yifang Mao
School of Mathematics and Computer Engineering,Xihua University,Chengdu Sichuan China Chengdu Railway Transportation School Chengdu Sichuan China
国际会议
北京
英文
2008-10-12（万方平台首次上网日期，不代表论文的发表时间）