Title :
Object matching on irregular pyramid
Author :
Pailloncy, Jean-Gerard ; Kropatsch, Walter ; Jolion, Jean-Michel
Author_Institution :
RFV, Inst. Nat. des Sci. Appliquees, Villeurbanne, France
Abstract :
The matching of an object, a region of an image segmentation, to a template is a heavy computation process and is not very robust. We represent an object by a region adjacency graph (RAG) on the top of which a pyramid (a decreasing sequence of RAG) is built according to a set of rules, which verify some uniqueness and uniformity properties. The contraction process preserves the structure of the RAG across the pyramid´s levels, and the rules are chosen according to the characteristics of the template. By building such a pyramid and then by a top-down process to match all the sub-graphs we have a linear parallel complexity time, with a robust match and a partial match relative to the given set of rules
Keywords :
computational complexity; graph theory; image matching; image segmentation; object recognition; complexity time; graph isomorphism; image segmentation; irregular pyramid; object recognition; pyramid levels; region adjacency graph; template matching; top-down process; uniformity; uniqueness; Buildings; Computer vision; Data structures; Image processing; Image segmentation; Kernel; Pattern matching; Pattern recognition; Reconnaissance; Robustness;
Conference_Titel :
Pattern Recognition, 1998. Proceedings. Fourteenth International Conference on
Conference_Location :
Brisbane, Qld.
Print_ISBN :
0-8186-8512-3
DOI :
10.1109/ICPR.1998.712056