Application of the Conditional Population-Mixture Model to Image Segmentation.
Abstract
The problem of image segmentation is considered in the context of a mixture of probability distributions. A modification of the usual approach to mixtures of distributions is employed. Parametric families of distributions are considered, a set of parameter values being associated with each distribution. In addition, an identification parameter is associated with each observation, indicating from which distribution the observation arose. Thus, the segmentation problem is cast as a problem of statistical estimation. Segmentation algorithms are obtained by applying a method of iterated maximum likelihood to the resulting likelihood function. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Aug 15, 1980
- Accession Number
- ADA088183
Entities
People
- Stanley L. Sclove
Organizations
- University of Illinois at Chicago