Logo image
Automated initialization and automated design of border detection criteria in edge-based image segmentation
Conference proceeding

Automated initialization and automated design of border detection criteria in edge-based image segmentation

M Brejl and M Sonka
4th IEEE Southwest Symposium on Image Analysis and Interpretation, Vol.2000-, pp.26-30
2000
DOI: 10.1109/IAI.2000.839565

View Online

Abstract

An automated model-based image segmentation method is presented. Information for image segmentation is automatically derived from a training set provided in a form of segmentation examples. In the first step, an approximate location of the object of interest is determined. In the second step, accurate border segmentation is performed. The method was tested in five different segmentation tasks that included 489 objects to be segmented. The final segmentation was compared to manually defined borders with good results. Two major problems of current edge-based image segmentation algorithms were addressed: strong dependence on a close-to-target initialization, and necessity for manual redesign of segmentation criteria whenever a new segmentation problem is encountered.
Active shape model Automation Cost function Dynamic programming Electrical capacitance tomography Electronic mail Image edge detection Image segmentation Pixel Spine

Details

Metrics

29 Record Views
Logo image