Two dimensional object recognition using multiresolution models
Computer Vision, Graphics, and Image Processing
HYPER: A New Approach for the Recognition and Positioning of Two-Dimensional Objects
IEEE Transactions on Pattern Analysis and Machine Intelligence
Machine interpretation of line drawings
Machine interpretation of line drawings
Efficient systematic analysis of occlusion
Pattern Recognition Letters
The complexity of recognizing polyhedral scenes
Journal of Computer and System Sciences - 26th IEEE Conference on Foundations of Computer Science, October 21-23, 1985
Hierarchy in Picture Segmentation: A Stepwise Optimization Approach
IEEE Transactions on Pattern Analysis and Machine Intelligence
Effectively Labeling Planar Projections of Polyhedra
IEEE Transactions on Pattern Analysis and Machine Intelligence
Partial Shape Recognition: A Landmark-Based Approach
IEEE Transactions on Pattern Analysis and Machine Intelligence
Visual occlusion and the interpretation of ambiguous pictures
Visual occlusion and the interpretation of ambiguous pictures
Analysis of 2-D Occlusion by Subtracting Out
IEEE Transactions on Pattern Analysis and Machine Intelligence
Fast parallel constraint satisfaction
Artificial Intelligence
The complexity of computing minimum separating polygons
Pattern Recognition Letters - Special issue on computational geometry
Characterising tractable constraints
Artificial Intelligence
On the complexity of labeling perspective projections of polyhedral scenes
Artificial Intelligence
An efficient parallel algorithm for geometrically characterising drawings of a class of 3-D objects
Journal of Mathematical Imaging and Vision
Filtering, Segmentation, and Depth
Filtering, Segmentation, and Depth
Computers and Intractability: A Guide to the Theory of NP-Completeness
Computers and Intractability: A Guide to the Theory of NP-Completeness
The Design and Analysis of Computer Algorithms
The Design and Analysis of Computer Algorithms
Polynomial-Time Object Recognition in the Presence of Clutter, Occlusion, and Uncertainty
ECCV '92 Proceedings of the Second European Conference on Computer Vision
Segmenting by Compression Using Linear Scale-Space and Watersheds
SCALE-SPACE '99 Proceedings of the Second International Conference on Scale-Space Theories in Computer Vision
Shape measures for image retrieval
Pattern Recognition Letters
Efficient Graph-Based Image Segmentation
International Journal of Computer Vision
Constraints Between Distant Lines in the Labelling of Line Drawings of Polyhedral Scenes
International Journal of Computer Vision
HPC-ICTM: the interval categorizer tessellation-based model for high performance computing
PARA'04 Proceedings of the 7th international conference on Applied Parallel Computing: state of the Art in Scientific Computing
Hi-index | 0.00 |
One of the fundamental problems in computer vision is thesegmentation of an image into semantically meaningful regions, basedonly on image characteristics. A single segmentation can bedetermined using a linear number of evaluations of a uniformitypredicate. However, minimising the number of regions is shown to bean NP-complete problem. We also show that the variational approach tosegmentation, based on minimising a criterion combining the overallvariance of regions and the number of regions, also gives rise to anNP-complete problem.When a library of object models is available, segmenting the imagebecomes a problem of scene analysis. A sufficient condition for thereconstruction of a 3D scene from a 2D image to be solvable inpolynomial time is that the scene contains no cycles of mutuallyoccluding objects and that no range information can be deduced fromthe image. It is known that relaxing the no cycles condition rendersthe problem NP-complete. We show that relaxing the no rangeinformation condition also produces an NP-complete problem.