Modelling visual objects invariant to depictive style

Qi Wu, Peter Hall

Research output: Contribution to conferencePaper

4 Citations (Scopus)

Abstract

Representing visual objects is an interesting open question of relevance to many important problems in Computer Vision such as classification and location. State of the art allows thousands of visual objects to be learned and recognised, under a wide range of variations including lighting changes, occlusion, point of view, and different object instances. Only a small fraction of the literature addresses the problem of variation in depictive style (photographs, drawings, paintings etc.), yet considering photographs and artwork on equal footing is philosophically appealing and of true practical significance. This paper describes a model for visual object classes that is learnable and which is able to classify over a broad range of depictive styles. The model is a graph in which simple shapes label region nodes. We use our model to classify twenty classes in CalTech 256, each class augmented by additional images to increase the variance in style. When compared to a Bag of Words classifier and to a structure only based classifier, our results show a significant increase in robustness to variance in depictive style.

Original languageEnglish
DOIs
Publication statusPublished - 1 Jan 2013
Event2013 24th British Machine Vision Conference, BMVC 2013 - Bristol, UK United Kingdom
Duration: 9 Sep 201313 Sep 2013

Conference

Conference2013 24th British Machine Vision Conference, BMVC 2013
CountryUK United Kingdom
CityBristol
Period9/09/1313/09/13

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Modelling visual objects invariant to depictive style'. Together they form a unique fingerprint.

Cite this