Synergism in low level vision
- 25 June 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4 (10514651) , 150-155
- https://doi.org/10.1109/icpr.2002.1047421
Abstract
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 over-segmentation on 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 technique and provides a complete toolbox for discontinuity preserving filtering, segmentation and edge detection.Keywords
This publication has 12 references indexed in Scilit:
- A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statisticsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Mean shift: a robust approach toward feature space analysisPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Edge detection with embedded confidencePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2001
- Automatic image segmentation by integrating color-edge extraction and seeded region growingIEEE Transactions on Image Processing, 2001
- Mean shift analysis and applicationsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1999
- Multiscale image segmentation by integrated edge and region detectionIEEE Transactions on Image Processing, 1997
- The integration of image segmentation maps using region and edge informationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1993
- A common framework for image segmentationInternational Journal of Computer Vision, 1991
- Image segmentation by unifying region and boundary informationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1990
- Integrating region growing and edge detectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1990