Article: Curvature product corner detection in direct curvature scale space Journal: International Journal of Computational Vision and Robotics (IJCVR) 2010 Vol.1 No.2 pp.194 - 205 Abstract: An efficient corner detector based on the direct curvature scale space (DCSS) technique, referred to as the curvature product direct curvature scale space (CP-DCSS) corner detector, is introduced and studied. The contours of interested objects are extracted from a real-world image, and then their curvature functions are respectively convolved with the Gaussian function, whose standard deviation gradually increases and is treated as a scale parameter of corner detection. By measuring the product of the curvature values computed at several given scales, true corners on the contours can be easily detected since false or insignificant corners have been effectively suppressed. A point is declared as a corner when the absolute value of the curvature product exceeds a given threshold and is a local maximum at the mentioned point. CP-DCSS combines the advantages of two recently proposed corner detectors, namely, the DCSS corner detector and the multi-scale curvature product (MSCP) corner detector. Compared to DCSS, CP-DCSS omits a parsing process of the DCSS map, and hence it has a simpler structure. Compared to MSCP, CP-DCSS works equally well, however, at less computational cost. Inderscience Publishers - linking academia, business and industry through research

Title: Curvature product corner detection in direct curvature scale space

Authors: Baojiang Zhong, Chang Li, Zhengsheng Wang

Addresses: School of Computer Science and Technology, Soochow University, Suzhou 215006, China; State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210093, China. ' Department of Mathematics, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China. ' Department of Mathematics, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China

Abstract: An efficient corner detector based on the direct curvature scale space (DCSS) technique, referred to as the curvature product direct curvature scale space (CP-DCSS) corner detector, is introduced and studied. The contours of interested objects are extracted from a real-world image, and then their curvature functions are respectively convolved with the Gaussian function, whose standard deviation gradually increases and is treated as a scale parameter of corner detection. By measuring the product of the curvature values computed at several given scales, true corners on the contours can be easily detected since false or insignificant corners have been effectively suppressed. A point is declared as a corner when the absolute value of the curvature product exceeds a given threshold and is a local maximum at the mentioned point. CP-DCSS combines the advantages of two recently proposed corner detectors, namely, the DCSS corner detector and the multi-scale curvature product (MSCP) corner detector. Compared to DCSS, CP-DCSS omits a parsing process of the DCSS map, and hence it has a simpler structure. Compared to MSCP, CP-DCSS works equally well, however, at less computational cost.

Keywords: corner detection; direct curvature scale space; computer vision.

DOI: 10.1504/IJCVR.2010.036081

International Journal of Computational Vision and Robotics, 2010 Vol.1 No.2, pp.194 - 205

Published online: 17 Oct 2010 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Curvature product corner detection in direct curvature scale space

Keep up-to-date