Open AccessModel-driven Selection using Texture
Author(s) -
Tanveer Syeda-Mahmood
Publication year - 1993
Publication title -
citeseer x (the pennsylvania state university)
Language(s) - English
Resource type - Conference proceedings
DOI - 10.5244/c.7.7
Subject(s) - artificial intelligence , pattern recognition (psychology) , computer science , texture (cosmology) , image texture , computer vision , texture compression , context (archaeology) , texture filtering , orientation (vector space) , segmentation , representation (politics) , matching (statistics) , bidirectional texture function , selection (genetic algorithm) , image segmentation , projective texture mapping , cognitive neuroscience of visual object recognition , object (grammar) , image (mathematics) , mathematics , paleontology , statistics , geometry , politics , political science , law , biology
In this paper we explore the use of texture or pattern information on a 3D object as a cue to isolate regions in an image that are likely to come from the object. We develop a representation of texture based on the linear prediction (LP) spectrum that allows the recognition of the model texture under changes in orientation and occlusions. The candidate matching image regions are obtained without detailed segmentation by a technique called overlapping window analysis. This analysis, under some conditions, guarantees the existence of a window spanning only the model texture regardless of its position and orientation which is sufficient for the recognition of the model texture using the LP spectrum representation. Finally, we evaluate the utility of texture-based selection in combination with other cues such as color in the context of reducing the search involved in recognition.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom