Segmentation of bright targets using wavelets and adaptive thresholding

A general systematic method for the detection and segmentation of bright ta rgets is developed in this paper. We use the term "bright target" to mean a connected, cohesive object which has an average intensity distribution abo ve that of the rest of the image. We develop an analytic model for the segm entation of targets, which uses a novel multiresolution analysis in concert with a Bayes classifier to identify the possible target areas. A method is developed which adaptively chooses thresholds to segment targets from back ground, by using a multiscale analysis of the image probability density fun ction (PDF), A performance analysis based on a Gaussian distribution model is used to show that the obtained adaptive threshold is often close to the Bayes threshold. The method has proven robust even when the image distribut ion is unknown. Examples are presented to demonstrate the efficiency of the technique on a variety of targets.