IEEE Transactions on Pattern Analysis and Machine Intelligence · 2001 · 110 citations · 56 references
ComputingComputer ScienceComputer VisionImage InterpretationMachine VisionImage SegmentationObject DetectionObject RecognitionShape AnalysisShape DeformationShape RepresentationDeformable ModelsDescription Length PrinciplesMinimum Description LengthPrior Model ProbabilitiesRegion-based RepresentationShape DetectionShape RecognitionStatistical Shape Analysis
A method for deformable shape detection and recognition is described. Deformable shape templates are used to partition the image into a globally consistent interpretation, determined in part by the minimum description length principle. Statistical shape models enforce the prior probabilities on global, parametric deformations for each object class. Once trained, the system autonomously segments deformed shapes from the background, while not merging them with adjacent objects or shadows. The formulation can be used to group image regions obtained via any region segmentation algorithm, e.g., texture, color, or motion. The recovered shape models can be used directly in object recognition. Experiments with color imagery are reported.
56
William H. Press, Saul A. Teukolsky, William T. Vetterling et al. · 1994 · 15.4K citations
Michael J. Swain, Dana H. Ballard · International Journal of Computer Vision · 1991 · 5.6K citations
Numerical Recipes--The Art of Scientific Computing.
Frederick N. Fritsch, William H. Press, Brian P. Flannery et al. · Mathematics of Computation · 1988 · 4.9K citations