An Adaptive Corner Detector Based on Curvature Scale Space
Haiyan Zhu · Computing Technology and Automation · 2007
The corner is an important feature in image processing,an adaptive corner detector is proposed based on curvature scale space technique in this paper.First,the contour curve is extracted for the image.According to the curvature calculated at a fix low scale for each point of the contour,corner candidates are obtained.Then,angles of corner candidates checked in an adaptive region of support and a dynamic curvature threshold are used instead of the fixed threshold to get true corners.Experimental results show that the proposed method offers an effective and robust solution to images containing widely different size features.