Spatial Priors for Part-Based Recognition Using Statistical Models
David Crandall, Pedro F. Felzenszwalb, Daniel P. Huttenlocher · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2005
We present a class of statistical models for part-based object recognition that are explicitly parameterized according to the degree of spatial structure they can represent. These models provide a way of relating different spatial priors that have been used for recognizing generic classes of objects, including joint Gaussian models and tree-structured models. By providing explicit control over the degree of spatial structure, our models make it possible to study the extent to which additional spatial constraints among parts are actually helpful in detection and localization, and to consider the tradeoff in representational power and computational cost. We consider these questions for object classes that have substantial geometric structure, such as airplanes, faces and motorbikes, using datasets employed by other researchers to facilitate evaluation. We find that for these classes of objects, a relatively small amount of spatial structure in the model can provide statistically indistinguishable recognition performance from more powerful models, and at a substantially lower computational cost.
Cited by 278 works. doi:10.1109/cvpr.2005.329
Authors
References
- Object class recognition by unsupervised scale-invariant learning
- The Representation and Matching of Pictorial Structures
- Pictorial Structures for Object Recognition
- A probabilistic approach to object recognition using local photometry and global geometry
- Probabilistic Methods for Finding People
- Recognition of planar object classes
- Configuration based scene classification and image indexing
- Efficient Synthesis of Gaussian Filters by Cascaded Uniform Filters
- 2D Object Detection and Recognition
- 2D Object Detection and Recognition: Models, Algorithms, and Networks