BMVC 2004, Kingston, 7th-9th Sept, 2004
Semi-Local Affine Parts for Object Recognition
S. Lazebnik (University of Illinois, USA), C. Schmid (INRIA, France) and
Jean Ponce (University of Illinois, USA)
This paper proposes a new approach for finding expressive and geometrically
invariant parts for modeling 3D objects. The approach relies on identifying
groups of local affine regions (image features having a characteristic appearance
and elliptical shape) that remain approximately affinely rigid across a
range of views of an object, and across multiple instances of the same object
class. These groups, termed semi-local affine parts, are learned using correspondence
search between pairs of unsegmented and cluttered input images,
followed by validation against additional training images. The proposed approach
is applied to the recognition of butterflies in natural imagery.
(pdf article)