Connected components in binary images: the detection problem
Connected components in binary images: the detection problem
IEEE Transactions on Pattern Analysis and Machine Intelligence
Knowledge-based real-time change detection, target image tracking & threat assessment
Proceedings of the NATO advanced research workshop on Machine intelligence and knowledge engineering for robotic applications
Parallel algorithm for corner finding on digital curves
Pattern Recognition Letters
Line thinning by line following
Pattern Recognition Letters
Corner characterization by differential geometry techniques
Pattern Recognition Letters
Machine vision system for inspecting electric plates
Computers in Industry
A rotationally invariant two-phase scheme for corner detection
Pattern Recognition
Image corner detection using hough transform
IbPRIA'05 Proceedings of the Second Iberian conference on Pattern Recognition and Image Analysis - Volume Part II
Hi-index | 0.15 |
The added functionality such as contour tracking and corner detection which logic programming lends to standard image operators is described. An environment for implementing low-level imaging operations with Prolog predicates is considered. Within this environment, higher-level image predicates (contour tracking and corner detection) are constructed. The emphasis is not on building better corner detectors, but on presenting ways of using the unification and backtracking features of logic programming for these tasks. The performance of this implementation of contour tracking and corner detection has been very good in many more complex images, as it allows for feedback both ways between sensor input and symbolic models. More important is the parameter selection capability in a dynamic version where background properties change. The authors present examples of Prolog predicates for performing the contour and corner detection operations.