OBJ CUT
Manish Kumar, Philip H. S. Torr, Andrew Zisserman · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2005
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.
Cited by 326 works. doi:10.1109/cvpr.2005.249
Authors
References
- Bayesian Data Analysis
- Object class recognition by unsupervised scale-invariant learning
- Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images
- What energy functions can be minimized via graph cuts?
- Learning a Sparse Representation for Object Detection
- Efficient matching of pictorial structures
- Class-Specific, Top-Down Segmentation
- Texture classification: are filter banks necessary?
- Recognizing surfaces using three-dimensional textons
- Interactive Image Segmentation Using an Adaptive GMMRF Model