A Wavelet Approach for Partial Occluded Object Recognition
A Wavelet Approach for Partial Occluded Object Recognition作者机构:Mechanical Engineering DepartmentNational University of SingaporeSingapone
出 版 物:《武汉理工大学学报》 (Journal of Wuhan University of Technology)
年 卷 期:2006年第28卷第S1期
页 面:32-39页
学科分类:0810[工学-信息与通信工程] 08[工学] 081002[工学-信号与信息处理]
主 题:wavelet partial occlusion object recognition corner detection
摘 要:A complete 2-D object recognition algorithm applicable for both standalone and partial occluded object is presented. The main contributions in our work are: we developed a scale and partial occlusion invariant boundary partition algorithm and a multiresolution feature extraction algorithm using wavelet. We also implemented a hierarchical matching strategy for feature matching to reduce computational load,but increase matching accuracy. Experiment result shows proposed recognition algorithm is robust to similarity transform and partial occlusion.