Deformable Shape Detection and Description via Model-Based Region Grouping
Date
1998-12-04
DOI
Authors
Liu, Lifeng
Sclaroff, Stan
Version
OA Version
Citation
Liu, Lifeng; Sclaroff, Stan. "Deformable Shape Detection and Description via Model-Based Region Grouping", Technical Report BUCS-1998-017, Computer Science Department, Boston University, December 4, 1998. [Available from: http://hdl.handle.net/2144/1773]
Abstract
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 based on any image homogeneity predicate; e.g., texture, color, or motion. The recovered shape models can be used directly in object recognition. Experiments with color imagery are reported.