Multiple Class Segmentation Using A Unified Framework over Mean-Shift Patches
Lin Yang, Peter Meer, David J. Foran · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2007
Object-based segmentation is a challenging topic. Most of the previous algorithms focused on segmenting a single or a small set of objects. In this paper, the multiple class object-based segmentation is achieved using the appearance and bag of keypoints models integrated over mean-shift patches. We also propose a novel affine invariant descriptor to model the spatial relationship of keypoints and apply the Elliptical Fourier Descriptor to describe the global shapes. The algorithm is computationally efficient and has been tested for three real datasets using less training samples. Our algorithm provides better results than other studies reported in the literature.
Cited by 121 works. doi:10.1109/cvpr.2007.383229
Authors
References
- Distinctive Image Features from Scale-Invariant Keypoints
- Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
- Normalized cuts and image segmentation
- Object class recognition by unsupervised scale-invariant learning
- Mean shift: a robust approach toward feature space analysis
- Learning generative visual models from few training examples: An incremental Bayesian approach tested on 101 object categories
- A performance evaluation of local descriptors
- Pictorial Structures for Object Recognition
- TextonBoost: Joint Appearance, Shape and Context Modeling for Multi-class Object Recognition and Segmentation
- Combined Object Categorization and Segmentation With An Implicit Shape Model