Title :
Aerial colour image segmentation by Karhunen-Loeve transform
Author :
Devaux, Jean-Christophe ; Gouton, Pierre ; Truchetet, Frédéic
Author_Institution :
Bourgogne Univ., Dijon, France
Abstract :
The Karhunen-Loeve transform (KLT) is used to perform region-based segmentation of aerial colour images from colour and texture features. A region-based segmentation method is developed in the KL colour image representation space and KLT is extended to texture analysis by local linear transform (LLT). An algorithm to merge colour and texture segmentation is presented in order to improve results
Keywords :
Karhunen-Loeve transforms; cartography; geography; image colour analysis; image representation; image segmentation; image texture; remote sensing; KL colour image representation space; KLT; Karhunen-Loeve transform; LLT; aerial colour image segmentation; colour features; colour segmentation; local linear transform; region-based segmentation; region-based segmentation method; texture analysis; texture features; texture segmentation; Classification algorithms; Councils; Covariance matrix; Eigenvalues and eigenfunctions; Energy measurement; Image color analysis; Image segmentation; Image texture analysis; Karhunen-Loeve transforms; Q measurement;
Conference_Titel :
Pattern Recognition, 2000. Proceedings. 15th International Conference on
Conference_Location :
Barcelona
Print_ISBN :
0-7695-0750-6
DOI :
10.1109/ICPR.2000.905335