Object Identification and Categorization with Visual Context: Hierarchical Graph

Description: Object Identification and Categorization with Visual Context by Sungho Kim, In So Kweon 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. FORMAT Paperback LANGUAGE English CONDITION Brand New Publisher Description 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 appli-cations 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 the guide 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 simi-larity 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. Author Biography 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. Details ISBN3639010337 Author In So Kweon Short Title OBJECT IDENTIFICATION & CATEGO Pages 208 Language English ISBN-10 3639010337 ISBN-13 9783639010336 Media Book Format Paperback Year 2008 Subtitle Hierarchical Graphical Model-based Approaches DOI 10.1604/9783639010336 UK Release Date 2008-05-07 Imprint VDM Verlag Dr. Mueller E.K. Country of Publication Germany Illustrations black & white illustrations Publisher VDM Verlag Dr. Mueller E.K. Publication Date 2008-05-07 Audience General We've got this At The Nile, if you're looking for it, we've got it. With fast shipping, low prices, friendly service and well over a million items - you're bound to find what you want, at a price you'll love! TheNile_Item_ID:132585608;

Price: 165.92 AUD

Location: Melbourne

End Time: 2025-01-06T16:01:09.000Z

Shipping Cost: 9.31 AUD