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.
Spatial priors for part-based recognition using statistical models
01.01.2005
352809 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Visual Saliency with Statistical Priors
British Library Online Contents | 2014
|Jointly Specified Spatial Priors for Bayesian Models of Crash Frequency
Transportation Research Record | 2018
|Reconstructing Magnetic Resonance Spectroscopic Images Using Spatial Domain Priors
British Library Conference Proceedings | 1994
|3D Human Pose Tracking Priors using Geodesic Mixture Models
British Library Online Contents | 2017
|Statistical Priors for Efficient Combinatorial Optimization Via Graph Cuts
British Library Conference Proceedings | 2006
|