摘要
在研究Harris角点检测算法时发现该算法对一些图像进行角点提取时,存在提取伪角点、角点信息丢失和位置偏移,而且在进行非极大值抑制时不易设置阈值等现象。提出了在进行非极大值抑制时采用双阈值法,分别设置一个相对大和一个相对小的两个阈值,从而得到同一图像不同阈值的角点信息,通过角点信息对比能够很好地解决角点信息丢失和位置偏移并能消除一部分伪角点,然后利用SUSAN的思想消除剩余的伪角点。通过对比实验表明,文中算法提取角点非常有效,比Harris算法具有更好的角点检测性能。
By the study of the Harris comer detection algorithm, while some images＇ corners are extracted, there exists the following problems： extracting false comers, the information of the comers is missing, the positioning of the comers offsets. And also not easy to set up the threshold in non- maximal inhibition. Presents to set up a dual threshold method, one is relatively large, and the other is relatively small when perform the non- maximal inhibition, so get the comers information of different thresholds in the same image, through comparing the comers information, can better solve the comers information missing,location offsetting and eliminate some false corners, and then using the idea of the SUSAN to eliminate the leaving false comers. By comparing the results show that the algorithm to extract comers very effective, and better than the Harris algorithm in the performance of comer detection.
出处
《计算机技术与发展》
2009年第5期130-133,共4页
Computer Technology and Development
基金
云南省自然科学基金项目(2007F2021X)
