A novel corner detector approach using sliding two ellipses and one rectangle
Zar Nawab Khan Swati, Safdar Zaman, Muhammad Sarfraz · 2009
This paper designs and implements a corner detection algorithm for generic shapes. The proposed corner detector detects corners by using combination of two ellipses and rectangle with different parameters sliding along the boundary of the shape and record number of boundary points in each ellipse and rectangle. This relationship represents both local and global view of the image which is a natural corners detection methodology to detect all true corners accurately. Proposed corner detection technique is consistent with human vision system.