dc.contributor.authorChia, Alex Yong Sang
dc.contributor.authorRajan, Deepu
dc.contributor.authorLeung, Maylor Karhang
dc.contributor.authorRahardja, Susanto
dc.date.accessioned2013-09-16T08:00:42Z
dc.date.available2013-09-16T08:00:42Z
dc.date.copyright2012en_US
dc.date.issued2012
dc.identifier.citationChia, A. Y.-S., Rajan, D., Leung, M. K., & Rahardja, S. (2012). Object Recognition by Discriminative Combinations of Line Segments, Ellipses, and Appearance Features. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(9), 1758-1772.
dc.identifier.issn0162-8828en_US
dc.identifier.urihttp://hdl.handle.net/10220/13495
dc.description.abstractWe present a novel contour-based approach that recognizes object classes in real-world scenes using simple and generic shape primitives of line segments and ellipses. Compared to commonly used contour fragment features, these primitives support more efficient representation since their storage requirements are independent of object size. Additionally, these primitives are readily described by their geometrical properties and hence afford very efficient feature comparison. We pair these primitives as shape-tokens and learn discriminative combinations of shape-tokens. Here, we allow each combination to have a variable number of shape-tokens. This, coupled with the generic nature of primitives, enables a variety of class-specific shape structures to be learned. Building on the contour-based method, we propose a new hybrid recognition method that combines shape and appearance features. Each discriminative combination can vary in the number and the types of features, where these two degrees of variability empower the hybrid method with even more flexibility and discriminative potential. We evaluate our methods across a large number of challenging classes, and obtain very competitive results against other methods. These results show the proposed shape primitives are indeed sufficiently powerful to recognize object classes in complex real-world scenes.en_US
dc.language.isoenen_US
dc.relation.ispartofseriesIEEE transactions on pattern analysis and machine intelligenceen_US
dc.rights© 2012 IEEEen_US
dc.subjectDRNTU::Engineering::Computer science and engineering
dc.titleObject recognition by discriminative combinations of line segments, ellipses, and appearance featuresen_US
dc.typeJournal Article
dc.contributor.schoolSchool of Computer Engineeringen_US
dc.identifier.doihttp://dx.doi.org/10.1109/TPAMI.2011.220


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record