The editing of picture segmentations using local analysis of graphs
- 1 April 1977
- journal article
- Published by Association for Computing Machinery (ACM) in Communications of the ACM
- Vol. 20 (4) , 223-229
- https://doi.org/10.1145/359461.359468
Abstract
A major problem in picture processing is the elimination of the large number of spurious regions that result from an initial segmentation by region growing techniques. Such regions have been eliminated either on the basis of semantic information or on the basis of size and contrast. A scheme is presented which performs eliminations on the basis of local properties of the region adjacency graph. The scheme is based on definitions of graph properties which are satisfied when a spurious region is present; then editing is equivalent to fast graph operations. A number of examples are shown.Keywords
This publication has 8 references indexed in Scilit:
- Picture Segmentation by a Tree Traversal AlgorithmJournal of the ACM, 1976
- Picture Segmentation by Texture DiscriminationIEEE Transactions on Computers, 1975
- A hierarchical data structure for picture processingComputer Graphics and Image Processing, 1975
- The generation of polygonal outlines of objects from gray level picturesIEEE Transactions on Circuits and Systems, 1975
- A boundary finding algorithm and its applicationsIEEE Transactions on Circuits and Systems, 1975
- Computer identification of visual surfacesComputer Graphics and Image Processing, 1973
- A region coloring technique for scene analysisCommunications of the ACM, 1973
- Edge and Curve Detection for Visual Scene AnalysisIEEE Transactions on Computers, 1971