OBJ CUT

• Published in: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) Vol. 1; pp. 18 - 25 vol. 1
• Main Authors: Kumar, M.P., Ton, P.H.S., Zisserman, A.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 2005
• Subjects: Bayesian methods; Cows; Horses; Image sampling; Image segmentation; Markov random fields; Object detection; Object recognition; Optimization methods; Shape
• ISBN: 0769523722; 9780769523729
• ISSN: 1063-6919; 1063-6919
• DOI: 10.1109/CVPR.2005.249

In this paper, we present a principled Bayesian method for detecting and segmenting instances of a particular object category within an image, providing a coherent methodology for combining top down and bottom up cues. The work draws together two powerful formulations: pictorial structures (PS) and Markov random fields (MRFs) both of which have efficient algorithms for their solution. The resulting combination, which we call the object category specific MRF, suggests a solution to the problem that has long dogged MRFs namely that they provide a poor prior for specific shapes. In contrast, our model provides a prior that is global across the image plane using the PS. We develop an efficient method, OBJ CUT, to obtain segmentations using this model. Novel aspects of this method include an efficient algorithm for sampling the PS model, and the observation that the expected log likelihood of the model can be increased by a single graph cut. Results are presented on two object categories, cows and horses. We compare our methods to the state of the art in object category specific image segmentation and demonstrate significant improvements.