Title :
Image semantic coding using OTB
Author :
Liénou, Marie ; Campedel, Marine
Author_Institution :
Inst. TELECOM, TELECOM ParisTech, Paris, France
Abstract :
Semantic coding is used to provide image representation able to make semantics emerge and to learn it. This process is based on a basic decomposition of the image content into ¿visual words¿; using spatial relationships, these visual words are aggregated to form structures and (inter)active learning is used to associate semantics to the emerging structures. A complete OTB tool has been developed to illustrate the whole process; it allows feature extraction and ¿visual words¿ production, as well as LDA and SVM learning approaches.
Keywords :
feature extraction; image coding; image representation; support vector machines; LDA; OTB; SVM learning; feature extraction; image representation; image semantic coding; visual words; Computer aided software engineering; Constraint theory; Design engineering; Image coding; Image processing; Remote sensing; Software algorithms; Software design; Software tools; State feedback; Classification; LDA; SVM; interpretation; visual words;
Conference_Titel :
Geoscience and Remote Sensing Symposium,2009 IEEE International,IGARSS 2009
Conference_Location :
Cape Town
Print_ISBN :
978-1-4244-3394-0
Electronic_ISBN :
978-1-4244-3395-7
DOI :
10.1109/IGARSS.2009.5417484
