[其它]A Corner Detector based on Global and Loc al Curvature Properties

Abstract ap{
2$k ,  
Corners play an important role in object identification in machine vision systems. Published corner detection based on single-scale can detect either fine or coarse features, but not both at the same time; whereas multi-scale detection performs well but computational intensive. This paper proposes a curvature based corner detector that detects both fine and coarse features accurately at low computational cost. First, it extracts contours from a Canny edge map. Second, it computes the absolute value of curvature of each point in a contour at a low scale and regards local maxima of absolute curvature as initial corner candidates. Third, it uses an adaptive curvature threshold to remove round corners from the initial list. Finally, false corners due to quantization noise and trivial details are eliminated by evaluating the angles of corner candidates in a dynamic region of support. The proposed detector was compared with popular corner detectors on planar curves and gr .. PJ2qfYsH=>  
Pv<24:ao  

未注册仅能浏览部分内容，查看全部内容及附件请先 登录 或 注册