DSpace Repository

Data and Model-Driven Selection Using Color Regions

Show simple item record

dc.creator Syeda-Mahmood, Tanveer Fathima
dc.date 2004-10-04T14:25:38Z
dc.date 2004-10-04T14:25:38Z
dc.date 1992-02-01
dc.date.accessioned 2013-10-09T02:42:20Z
dc.date.available 2013-10-09T02:42:20Z
dc.date.issued 2013-10-09
dc.identifier AIM-1270
dc.identifier http://hdl.handle.net/1721.1/5994
dc.identifier.uri http://koha.mediu.edu.my:8181/xmlui/handle/1721
dc.description A key problem in model-based object recognition is selection, namely, the problem of determining which regions in the image are likely to come from a single object. In this paper we present an approach that extracts and uses color region information to perform selection either based solely on image- data (data-driven), or based on the knowledge of the color description of the model (model -driven). The paper presents a method of perceptual color specification by color categories to extract perceptual color regions. It also discusses the utility of color-based selection in reducing the search involved in recognition.
dc.format 29 p.
dc.format 4497036 bytes
dc.format 1782485 bytes
dc.format application/postscript
dc.format application/pdf
dc.language en_US
dc.relation AIM-1270
dc.subject selection
dc.subject color
dc.subject recognition
dc.subject saliency
dc.subject visual attention
dc.subject sregion segmentation
dc.title Data and Model-Driven Selection Using Color Regions


Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account