Invariant Shape Matching for Detection of Semi-local Image Structures

Authors:
Lech Szumilas;Horst Wildenauer;Allan Hanbury
Affiliations:
Vienna University of Technology, Wien, Austria A-1040;Vienna University of Technology, Wien, Austria A-1040;Vienna University of Technology, Wien, Austria A-1040
Venue:
ICIAR '09 Proceedings of the 6th International Conference on Image Analysis and Recognition
Year:
2009

Citing 4
Cited 0

Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)
Scale & Affine Invariant Interest Point Detectors

International Journal of Computer Vision
Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive Study

International Journal of Computer Vision
Object localization based on Markov random fields and symmetry interest points

MICCAI'07 Proceedings of the 10th international conference on Medical image computing and computer-assisted intervention

Quantified Score

Hi-index	0.01

Visualization

Abstract

Shape features applied to object recognition has been actively studied since the beginning of the field in 1950s and remain a viable alternative to appearance based methods e.g. local descriptors. This work address the problem of learning and detecting repeatable shape structures in images that may be incomplete, contain noise and/or clutter as well as vary in scale and orientation. A new approach is proposed where invariance to image transformations is obtained through invariant matching rather than typical invariant features. This philosophy is especially applicable to shape features such as open edges which do not have a specific scale or specific orientation until assembled into an object. Our primary contributions are: a new shape-based image descriptor that encodes a spatial configuration of edge parts, a technique for matching descriptors that is rotation and scale invariant and shape clustering that can extract frequently appearing image structures from training images without a supervision.