Sciweavers

ECCV
2010
Springer

Image Segmentation with Topic Random Field

13 years 5 months ago
Image Segmentation with Topic Random Field
Abstract. Recently, there has been increasing interests in applying aspect models (e.g., PLSA and LDA) in image segmentation. However, these models ignore spatial relationships among local topic labels in an image and suffers from information loss by representing image feature using the index of its closest match in the codebook. In this paper, we propose Topic Random Field (TRF) to tackle these two problems. Specifically, TRF defines a Markov Random Field over hidden labels of an image, to enforce the spatial coherence between topic labels for neighboring regions. Moreover, TRF utilizes a noise channel to model the generation of local image features, and avoids the off-line process of building visual codebook. We provide details of variational inference and parameter learning for TRF. Experimental evaluations on three image data sets show that TRF achieves better segmentation performance.
Added 12 Oct 2010
Updated 12 Oct 2010
Type Conference
Year 2010
Where ECCV
Comments (0)