An improved corner detection algorithm based on chain-coded plane curves
Pattern Recognition
Corner detection from chain-code
Pattern Recognition
Scale-Based Detection of Corners of Planar Curves
IEEE Transactions on Pattern Analysis and Machine Intelligence
An algorithm for detection of dominant points and polygonal approximation of digitized curves
Pattern Recognition Letters
Boundary-based corner detection using eigenvalues of covariance matrices
Pattern Recognition Letters
A Corner-Finding Algorithm for Chain-Coded Curves
IEEE Transactions on Computers
A mean field annealing approach to robust corner detection
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
A novel approach to polygonal approximation of digital curves
Journal of Visual Communication and Image Representation
Technical Section: Corner detection by sliding rectangles along planar curves
Computers and Graphics
Optimized polygonal approximation by dominant point deletion
Pattern Recognition
Dominant point detection by reverse polygonization of digital curves
Image and Vision Computing
Information overlay for camera phones in indoor environments
LoCA'07 Proceedings of the 3rd international conference on Location-and context-awareness
Polygonal approximation of digital planar curves through adaptive optimizations
Pattern Recognition Letters
Feature-based tracking approach for detection of moving vehicle in traffic videos
Proceedings of the First International Conference on Intelligent Interactive Technologies and Multimedia
Machine vision based automatic separation of touching convex shaped objects
Computers in Industry
Hi-index | 0.00 |
In this paper, a novel boundary based corner detection algorithm isproposed. The proposed algorithm is computationally fast andefficient. The proposed method computes an expected point forevery point on a boundary curve. An expected point correspondingto a point on the boundary curve is defined to be the geometricalcentroid of the symmetrical boundary segment of size 2k+1, forsome integer k 0, within the neighborhood of the point inconsideration. A new ýcornerityý index for a point on the boundarycurve is defined to be the distance between the point and itscorresponding expected point. The larger the cornerity index, thestronger is the evidence that the boundary point is a corner point. Aset of rules is worked out to guide the process of locating truecorner points. The conducted experiments establish that theproposed approach is invariant to image transformations viz.,rotation, translation and scaling.