Skip to main content
eScholarship
Open Access Publications from the University of California

Department of Statistics, UCLA

Department of Statistics Papers bannerUCLA

Object Perception as Bayesian Inference

Abstract

We perceive the shapes and material properties of ob jects quickly and reliably despite the complexity and ob jective ambiguities of natural images. Typical images are highly complex because they consist of many ob jects embedded in background clutter. Moreover, the image features of an ob ject are extremely variable and ambiguous due to the effects of pro jection, occlusion, background clutter, and illumination. The very success of everyday vision implies neural mechanisms, yet to be understood, that discount irrelevant information and organize ambiguous or “noisy” local image features into ob jects and surfaces. Recent work in Bayesian theories of visual perception has shown how complexity may be managed and ambiguity resolved through the task-dependent, probabilistic integration of prior ob ject knowledge with image features.

Main Content
For improved accessibility of PDF content, download the file to your device.
Current View