DocumentCode
2619019
Title
Early jump-out corner detectors
Author
Cooper, J. ; Venkatesh, S. ; Kitchen, L.
Author_Institution
Dept. of Comput. Sci., Western Australia Univ., Nedlands, WA, Australia
fYear
1991
fDate
3-6 Jun 1991
Firstpage
688
Lastpage
689
Abstract
Two corner detectors are presented, one of which works by testing similarity of image patches along the contour direction to detect curves in the image contour, and the other of which uses direct estimation image curvature along the contour direction. The operators are fast, robust to noise, and self-thresholding. An interpretation of the Kitchen-Rosenfeld corner operator is presented which shows that this operator can also be viewed as the second derivative of the image function along the edge direction
Keywords
pattern recognition; picture processing; Kitchen-Rosenfeld corner operator; contour direction; corner detectors; curves; direct estimation image curvature; early jump-out detectors; image contour; image patches; self-thresholding; Australia; Detectors; Image analysis; Image edge detection; Image motion analysis; Image segmentation; Motion detection; Noise robustness; Quantization; Testing;
fLanguage
English
Publisher
ieee
Conference_Titel
Computer Vision and Pattern Recognition, 1991. Proceedings CVPR '91., IEEE Computer Society Conference on
Conference_Location
Maui, HI
ISSN
1063-6919
Print_ISBN
0-8186-2148-6
Type
conf
DOI
10.1109/CVPR.1991.139783
Filename
139783
Link To Document