Synergism in Low Level Vision

Guiding image segmentation with edge information is an often employed strategy in low level computer vision. To improve the trade-off between the sensitivity of homogeneous region delineation and the oversegmentation of the image, we have incorporated a recently proposed edge magnitude/confidence map into a color image segmenter based on the mean shift procedure. The new method can recover regions with weak but sharp boundaries and thus can provide a more accurate input for high level interpretation modules. The Edge Detection and Image SegmentatiON (EDISON) system, available for download, implements the proposed techniqueand provides a complete toolbox for discontinuity preserving filtering, segmentation and edge detection.

• Type: Conference
• Year: 2002
• Where: ICPR
• Authors: Christopher M. Christoudias, Bogdan Georgescu, Peter Meer
• Keywords: Computer Vision, Edge Detection, Edge Magnitude/confidence Map, ICPR 2002, Image Segmentation