Abstract | ||
---|---|---|
In this paper, we propose a robust corner detection method to improve both detection rate and localization accuracy by modifying the structure tensor-based corner detection method in two ways. First, we introduce a connected component analysis (CCA) method for constructing a CCA structure tensor in order to make the structure tensor adaptive to the structure of the image. Second, the normalized cross-correlation (NCC) method is applied for false corner rejection with the observation that the patch of a true corner has a distinctive characteristic compared with connected neighboring patches. The proposed method is compared with several corner detection methods over a number of images. Experimental results show that the proposed method shows better performance in terms of both detection rate and localization accuracy. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1007/s00034-012-9388-z | CSSP |
Keywords | Field | DocType |
Corner,Connected component analysis,Structure tensor,Normalized cross correlation | Cross-correlation,Normalization (statistics),Pattern recognition,Corner detection,Structure tensor,Artificial intelligence,Connected-component labeling,Image structure,Mathematics | Journal |
Volume | Issue | ISSN |
31 | 4 | 0278-081X |
Citations | PageRank | References |
2 | 0.38 | 12 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Bongjoe Kim | 1 | 7 | 2.26 |
Ji-Hoon Choi | 2 | 4 | 0.73 |
Yong Woon Park | 3 | 32 | 10.14 |
Kwanghoon Sohn | 4 | 1041 | 110.23 |