期刊
JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING
卷 11, 期 5, 页码 2061-2070出版社
SPRINGER HEIDELBERG
DOI: 10.1007/s12652-019-01232-2
关键词
Edge detection; Sub-pixel; Roberts operator; Zernike moment; Otsu's method
类别
资金
- National Natural Science Foundation of China [61762037, 61872141, 61462028]
- Natural Science Foundation of Jiangxi Province [20181BAB206037]
- Excellent Scientific and Technological Innovation Teams of Jiangxi Province [20181BCB24009]
- Nanchang City Knowledge Innovation Team [2016T75]
In this paper, an improved sub-pixel edge detection algorithm combining coarse and precise location is proposed. The algorithm fully considers the 8-neighborhood pixel information and keeps the Roberts operator's advantages of high location accuracy and fast speed. Meanwhile, it can effectively suppress noise and obtain better detection results. In order to solve the problem of low efficiency of the Zernike moment method in threshold selection, the Otsu's method is introduced to achieve accurate sub-pixel edge location. The experimental results show that the proposed algorithm effectively improves the detection efficiency and the detection accuracy.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据