Title :
A very efficient strategy for very large data sets clustering: application to image segmentation
Author_Institution :
Lab. d´´Astron. Spatiale, CNRS, Marseille, France
Abstract :
The clustering strategy for very large data sets that is presented overcomes the limits of the classical strategy based on the clustering of the so-called strong patterns. The strategy presented leads to results of high statistical quality and is at least 25 times faster than the classical strategy in the case of the clustering of about 10000 pixels coming from a sensitometry image
Keywords :
computerised pattern recognition; computerised picture processing; image segmentation; pattern recognition; picture processing; sensitometry image; very large data sets clustering; Acceleration; Clustering algorithms; Clustering methods; High level synthesis; Image analysis; Image segmentation; Pixel; Principal component analysis;
Conference_Titel :
Pattern Recognition, 1988., 9th International Conference on
Conference_Location :
Rome
Print_ISBN :
0-8186-0878-1
DOI :
10.1109/ICPR.1988.28309
