Segmentation and boundary detection using multiscale intensity measurements
- 25 August 2005
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001
- p. 469-476
- https://doi.org/10.1109/cvpr.2001.990512
Abstract
Image segmentation is difficult because objects may dif- fer from their background by any of a variety of properties that can be observed in some, but often not all scales. A further complication is that coarse measurements, applied to the image for detecting these properties, often average over properties of neighboring segments, making it diffi- cult to separate the segments and to reliably detect their boundaries. Below we present a method for segmentation that generates and combines multiscale measurements of in- tensity contrast, texture differences, and boundary integrity. The method is based on our former algorithm SWA, which efficiently detects segments that optimize a normalized-cut- like measure by recursively coarsening a graph reflecting similarities between intensities of neighboring pixels. In this process aggregates of pixels of increasing size are grad- ually collected to form segments. We intervene in this pro- cess by computing properties of the aggregates and modi- fying the graph to reflect these coarse scale measurements. This allows us to detect regions that differ by fine as well as coarse properties, and to accurately locate their bound- aries. Furthermore, by combining intensity differences with measures of boundary integrity across neighboring aggre- gates we can detect regions separated by weak, yet consis- tent edges.Keywords
This publication has 21 references indexed in Scilit:
- Normalized cuts and image segmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000
- Completion energies and scaleIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000
- Local scale control for edge detection and blur estimationIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998
- Image segmentation by a multiresolution approachPattern Recognition, 1993
- An optimal graph theoretic approach to data clustering: theory and its application to image segmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 1993
- Variable pyramid structures for image segmentationComputer Vision, Graphics, and Image Processing, 1990
- Integrating region growing and edge detectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 1990
- The Laplacian Pyramid as a Compact Image CodeIEEE Transactions on Communications, 1983
- Split-and-link algorithms for image segmentationPattern Recognition, 1982
- Picture Segmentation by a Tree Traversal AlgorithmJournal of the ACM, 1976