Title :
Appearance Modeling Using a Geometric Transform
Author :
Li, Jian ; Zhou, Shaohua Kevin ; Chellappa, Rama
Author_Institution :
Goldman Sachs & Co., New York, NY
fDate :
4/1/2009 12:00:00 AM
Abstract :
A general transform, called the geometric transform (GeT), that models the appearance inside a closed contour is proposed. The proposed GeT is a functional of an image intensity function and a region indicator function derived from a closed contour. It can be designed to combine the shape and appearance information at different resolutions and to generate models invariant to deformation, articulation, or occlusion. By choosing appropriate functionals and region indicator functions, the GeT unifies Radon transform, trace transform, and a class of image warpings. By varying the region indicator and the types of features used for appearance modeling, five novel types of GeTs are introduced and applied to fingerprinting the appearance inside a contour. They include the GeTs based on a level set, shape matching, feature curves, and the GeT invariant to occlusion, and a multiresolution GeT (MRGeT). Applications of GeT to pedestrian identity recognition, human body part segmentation, and image synthesis are illustrated. The proposed approach produces promising results when applied to fingerprinting the appearance of a human and body parts despite the presence of nonrigid deformations and articulated motion.
Keywords :
Radon transforms; computational geometry; image resolution; image segmentation; Radon transform; appearance modeling; closed contour; feature curve; fingerprinting; geometric transform; human body part segmentation; image intensity function; image synthesis; image warping; level set method; pedestrian identity recognition; region indicator function; shape matching; trace transform; Biological system modeling; Deformable models; Fingerprint recognition; Humans; Image generation; Image recognition; Image segmentation; Level set; Shape; Solid modeling; Appearance model; Radon transform; geometric transform (GeT); human body part segmentation; image warping; interpolation; invariant feature; level set; multiresolution; pedestrian identity recognition; shape matching; trace transform;
Journal_Title :
Image Processing, IEEE Transactions on
DOI :
10.1109/TIP.2008.2011381