Deformable shape detection and description via model-based region grouping

A method for deformable shape detection and recognition is described. Defor mable shape templates are used to partition the image into a globally consi stent interpretation, determined in part by the minimum description length principle. Statistical shape models enforce the prior probabilities on glob al, parametric deformations for each object class. Once trained, the system autonomously segments deformed shapes from the background, while not mergi ng them with adjacent objects or shadows. The formulation can be used to gr oup image regions obtained via any region segmentation algorithm, e.g., tex ture. color, or motion. The recovered shape models can be used directly in object recognition. Experiments with color imagery are reported.