Object-based image labeling through learning by example and multi-level segmentation

Show simple item record

dc.contributor.author Xu, Y.
dc.contributor.author Duygulu, P.
dc.contributor.author Saber, Eli
dc.contributor.author Tekalp, A.
dc.contributor.author Yarman-Vural, F.
dc.date.accessioned 2008-06-19T19:49:50Z
dc.date.available 2008-06-19T19:49:50Z
dc.date.issued 2003-06
dc.identifier.citation Xu, Y., Duygulu, P., Saber, E., Tekalp, A., & Yarman-Vural, F., "Object-based image labeling through learning by example and mutl-level segmentation," Pattern Recognition, vol. 36, no. 6, pp.1407-1423. (2003) en_US
dc.identifier.uri http://hdl.handle.net/1850/6297
dc.description Journal Webpage: http://www.elsevier.com/wps/find/journaldescription.cws_home/328/description#description en_US
dc.description RIT community members may access full-text via RIT Libraries licensed databases: http://library.rit.edu/databases/
dc.description.abstract We propose a system that employs low-level image segmentation followed by color and two-dimensional (2-D) shape matching to automatically group those low-level segments into objects based on their similarity to a set of example object templates presented by the user. A hierarchical content tree data structure is used for each database image to store matching combinations of low-level regions as objects. The system automatically initializes the content tree with only “elementary nodes” representing homogeneous low-level regions. The “learning” phase refers to labeling of combinations of low-level regions that have resulted in successful color and/or 2-D shape matches with the example template( s). These combinations are labeled as “object nodes” in the hierarchical content tree. Once learning is performed, the speed of second-time retrieval of learned objects in the database increases significantly. The learning step can be performed off-line provided that example objects are given in the form of user interest profiles. Experimental results are presented to demonstrate the effectiveness of the proposed system with hierarchical content tree representation and learning by color and 2-D shape matching on collections of car and face images. en_US
dc.language.iso en_US en_US
dc.publisher Elsevier Science en_US
dc.relation.ispartofseries vol.36 en_US
dc.relation.ispartofseries no.6 en_US
dc.subject Color matching en_US
dc.subject Learning from examples en_US
dc.subject Object annotation en_US
dc.subject Semantic object segmentation en_US
dc.subject Shape matching en_US
dc.title Object-based image labeling through learning by example and multi-level segmentation en_US
dc.type Postprint en_US

Files in this item

Files Size Format View

An open access version of this file is not available. Check "Publisher URL" field for access

This item appears in the following Collection(s)

Show simple item record

Search RIT DML


Advanced Search

Browse