Image corner detection method based on multi-scale discrete curvature
| Autor: | Junfeng JING, Jiurui SUN, Weichuan ZHANG, Mengmeng BAI |
|---|---|
| Jazyk: | čínština |
| Rok vydání: | 2021 |
| Předmět: | |
| Zdroj: | Xi'an Gongcheng Daxue xuebao, Vol 35, Iss 5, Pp 27-33 (2021) |
| Druh dokumentu: | article |
| ISSN: | 1674-649X 1674-649x |
| DOI: | 10.13338/j.issn.1674-649x.2021.05.005 |
| Popis: | The traditional curvature calculation method is sensitive to local changes and noise in the discrete domain, which makes the corner detection accuracy and location deviate. In order to solve the above problems, a multi-scale discrete curvature is proposed to calculate the curvature and detect corners. Firstly, Canny edge detector was used to process the input image to obtain a binary edge image, then the edge contour was extracted from the edge image, the gap was filled along the contour, and T-shaped corners were detected and marked. Secondly, under three different smoothing scales, Gaussian function was used to smooth each plane curve, and then a new curvature measurement method was used to calculate the curvature of each point on each contour after smoothing, and the local maximum point of absolute curvature was taken as the candidate corner point of each scale. Finally, the curvature value of candidate corners was compared with the curvature threshold. The points greater than the curvature threshold were defined as candidate real corners, and the candidate corners that could be detected at three scales were regarded as real corners. The experimental results show that when the algorithm is used to detect the standard corner data laboratory image, the correct corner number is 159, the wrong corner number is 90, the missing corner number is 16, and the localization error is 1.257 2, and that when the standard corner data block image is tested, the detected correct corner number is 46, the wrong corner number is 13, the missing corner number is 1, and the localization error is 1.013 2. Compared with the existing three classical corner detection algorithms, the detection method in this paper has better corner detection performance. |
| Databáze: | Directory of Open Access Journals |
| Externí odkaz: |
|