Object matching using deformable templates
Anil Kumar Jain, Yu Zhong, Sridhar Lakshmanan · IEEE Transactions on Pattern Analysis and Machine Intelligence · 1996
We propose a general object localization and retrieval scheme based on object shape using deformable templates. Prior knowledge of an object shape is described by a prototype template which consists of the representative contour/edges, and a set of probabilistic deformation transformations on the template. A Bayesian scheme, which is based on this prior knowledge and the edge information in the input image, is employed to find a match between the deformed template and objects in the image. Computational efficiency is achieved via a coarse-to-fine implementation of the matching algorithm. Our method has been applied to retrieve objects with a variety of shapes from images with complex background. The proposed scheme is invariant to location, rotation, and moderate scale changes of the template.
Cited by 520 works. doi:10.1109/34.485555
Authors
References
- Equation of State Calculations by Fast Computing Machines
- Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
- Snakes: Active contour models
- Use of the Hough transformation to detect lines and curves in pictures
- Generalizing the Hough transform to detect arbitrary shapes
- Feature extraction from faces using deformable templates
- Feature extraction from faces using deformable templates
- A survey of the hough transform
- Efficient and effective Querying by Image Content
- Hands: A Pattern Theoretic Study of Biological Shapes