Regions adjacency graph applied to color image segmentation

• Published in: IEEE transactions on image processing Vol. 9; no. 4; pp. 735 - 744
• Main Authors: Tremeau, A., Colantoni, P.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01-04-2000; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithm design and analysis; Automatic testing; Clustering algorithms; Color; Computers in experimental physics; Exact sciences and technology; Fundamental areas of phenomenology (including applications); Graphs; Image color analysis; Image forming and processing; Image processing; Image segmentation; Imaging and optical processing; Instruments, apparatus, components and techniques common to several branches of physics and astronomy; Iterative algorithms; Large Hadron Collider; Optics; Physics; Region 8; Robustness; Segmentation; Segments; Transformations; Algorithms; Segmentation; Image processing; Adjustments; Experimental study; Color image; Image method; Weight
• ISSN: 1057-7149; 1941-0042
• DOI: 10.1109/83.841950

This paper presents different algorithms, based on a combination of two structures of a graph and of two color image processing methods, in order to segment color images. The structures used in this study are the region adjacency graph and the associated line graph. We see how these structures can enhance segmentation processes such as region growing or watershed transformation. The principal advantage of these structures is that they give more weight to the adjacency relationships between regions than the usual methods. We note, nevertheless, that this advantage leads the adjustment of more parameters than other methods to best refine the result of the segmentation. We show that this adjustment is necessarily image dependent and observer dependent.