基于图像分块的多尺度Harris特征点检测算法  

Multi-scale Harris Algorithm for Feature Point Detection Based on Image Sub-block

作　　者：王立中[1] 麻硕士[1] 薛河儒[1] 侯振杰[1] 

机构地区：[1]内蒙古农业大学机电工程学院,呼和浩特010018

出　　处：《内蒙古大学学报（自然科学版）》2009年第3期326-329,共4页Journal of Inner Mongolia University：Natural Science Edition

基　　金：教育部"春晖计划"资助项目(Z2007-1-01010)

摘　　要：通过分析H arris特征点检测算法在应用中的不足,提出一种基于图像分块的多尺度H arris特征点检测算法,解决了特征点聚簇现象,检测出的特征点分布均匀.实验结果表明,该算法具有精确性、有效性和鲁棒性,为进一步图像特征点匹配工作提供了保证.Based on the shortcoming of Harris algorithm in application, a multi-scale Harris algorithm for the feature point detection based on image sub-block is proposed. It makes the detected feature points well-proportioned distributed without clusters. Experiments demonstrate that this algorithm has a good performance of accuracy,validity and robustness, which provides a guarantee for the further matching of feature points

关 键 词：特征点检测 HARRIS算法 多尺度 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]