UCL logo

UCL Discovery

UCL home » Library Services » Electronic resources » UCL Discovery

Epitomized Priors for Multi-labeling Problems

Warrell, J; Prince, SJD; Moore, AP; (2009) Epitomized Priors for Multi-labeling Problems. In: CVPR: 2009 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOLS 1-4. (pp. 2804 - 2811). IEEE

Full text not available from this repository.

Abstract

Image parsing remains difficult due to the need to combine local and contextual information when labeling a scene. We approach this problem by using the epitome as a prior over label configurations. Several properties make it suited to this task. First, it allows a condensed patch-based representation. Second, efficient E-M based learning and inference algorithms can he used. Third, non-stationarity is easily incorporated. We consider three existing priors, and show how each can be extended using the epitome. The simplest prior assumes patches of labels are drawn independently from either a mixture model or an epitome. Next we investigate a 'conditional epitome' model, which substitutes an epitome for a conditional mixture model. Finally, we develop an 'epitome tree' model, which combines the epitome with a tree structured belief network prior Each model is combined with a per-pixel classifier to perform segmentation. In each case, the epitomized form of the prior provides superior segmentation performance, with the epitome tree performing best overall. We also apply the same models to denoising binary images, with similar results.

Type:Proceedings paper
Title:Epitomized Priors for Multi-labeling Problems
Event:IEEE-Computer-Society Conference on Computer Vision and Pattern Recognition Workshops
Location:Miami Beach, FL
Dates:2009-06-20 - 2009-06-25
ISBN-13:978-1-4244-3992-8
Keywords:IMAGE SEGMENTATION, RECOGNITION
UCL classification:UCL > School of BEAMS > Faculty of Engineering Science > Computer Science

Archive Staff Only: edit this record