HYPER: A New Approach for the Recognition and Positioning of Two-Dimensional Objects
IEEE Transactions on Pattern Analysis and Machine Intelligence
Localizing Overlapping Parts by Searching the Interpretation Tree
IEEE Transactions on Pattern Analysis and Machine Intelligence
Using Polygons to Recognize and Locate Partially Occluded Objects
IEEE Transactions on Pattern Analysis and Machine Intelligence
Efficient systematic analysis of occlusion
Pattern Recognition Letters
The Tractability of Segmentation and Scene Analysis
International Journal of Computer Vision
Hi-index | 0.14 |
A provably correct polynomial-time algorithm for complete systematic analysis of occlusion in synthetically generated noise-free pictures of 2-D objects is introduced. The algorithm first recognizes occluding objects and then ignores the mismatch with pixels in occluding objects while recognizing occluded objects by template matching.