Simultaneous bottom-up/top-down processing in early and mid level vision

Date

2008

Author

Erdem, Mehmet Erkut

Metadata

Show full item record

Item Usage Stats

2
views

0
downloads

The prevalent view in computer vision since Marr is that visual perception is a data-driven bottom-up process. In this view, image data is processed in a feed-forward fashion where a sequence of independent visual modules transforms simple low-level cues into more complex abstract perceptual units. Over the years, a variety of techniques has been developed using this paradigm. Yet an important realization is that low-level visual cues are generally so ambiguous that they could make purely bottom-up methods quite unsuccessful. These ambiguities cannot be resolved without taking account of high-level contextual information. In this thesis, we explore different ways of enriching early and mid-level computer vision modules with a capacity to extract and use contextual knowledge. Mainly, we integrate low-level image features with contextual information within unied formulations where bottom-up and top-down processing take place simultaneously.

Subject Keywords

Computer science.

URI

http://etd.lib.metu.edu.tr/upload/12610167/index.pdf
https://hdl.handle.net/11511/17979

Collections

Graduate School of Natural and Applied Sciences, Thesis