Object Identification and Categorization with Visual Context: Hierarchical Graphical Model-based Approaches - Brossura

Kim, Sungho; So Kweon, In

Brossura

ISBN 10: 3639010337 ISBN 13: 9783639010336

Casa editrice: VDM Verlag Dr. Müller, 2008

Riassunto

The goal of object recognition is to label objects from images and to estimate the poses of the labeled objects. The field of object recognition has seen tremendous progress with successful applications in some specific domains such as face recognition. However, the current state-of-the-art methods show unsatisfactory results for more general object domains in complex natural environments with visual ambiguities. In this dissertation, we aim to enhance the object identification and categorization with theguide of visual context and graphical model. In this work, we propose a general framework for the cooperative object identification and object categorization. Examplars used in identification provide useful information of similarity in categorization. Conversely, novel objects are rejected in identification but the proposed object categorization can label the novel objects and segment them out for database update in identification. This work can be helpful to the engineers in artificial intelligence and machine vision.

Su questo libro

L'autore

Sungho Kim#201 111-7, Eoeun-dong Yuseong-gu, Daejeon, Korea, 305-333Senior Researcher at the Agency for Defense Development, 2007~Current.Korea Advanced Institute of Science and Technology (KAIST), Ph.D. Degree, 2007.Korea Advanced Institute of Science and Technology (KAIST), M.S., 2002.Korea University, B.S., 2000.

Dettagli dell'edizione

• Editore: VDM Verlag Dr. Müller
• Data di pubblicazione: 2008
• Lingua: Inglese
• ISBN 10: 3639010337
• ISBN 13: 9783639010336
• Rilegatura: Copertina flessibile
• Numero di pagine: 208
• Contatto del produttore: non disponibile
• Persona responsabile: non disponibile