A robust edge detection method with sub-pixel accuracy |
| |
| Authors: | Qiucheng Sun Yueqian Hou Qingchang Tan Chunjing Li Ming Liu |
| |
| Affiliation: | 1. College of Basic Science, Changchun University of Technology, Yanan Street 2055, Changchun, China;2. College of Mechanical Science and Engineering, Changchun University, Changchun, China;3. College of Mechanical Science and Engineering, Jilin University, Changchun, China |
| |
| Abstract: | In this paper, a new edge detection approach combining gray-moments operator with smoothing spline algorithm is proposed, which is invariant to additive and multiplicative noises in the image. This approach consists of two steps: firstly, a continuous blurred edge model is obtained using the smoothing spline algorithm in the edge region detected by Sobel operator; then a gray-moment solution is derived for both the one- and two-dimensional situations using the blurred edge model. Testing of this new detection approach demonstrates more robustness against the white Gaussian noise and speckle noise, and run time very close to the gray-moment and space-moment operators. The above advantages indicate this approach is very suitable for on-line accurate detection. |
| |
| Keywords: | Sub-pixel edge detection Sobel operator Gray-moment Smoothing spline algorithm |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
