Rotation-invariant pattern signature

Research output: Contribution to conferencePaper

Abstract

We propose a 'signature' for rotation-invariant representation of local image structure. The signature is a complex-valued vector constructed analytically from the projections of the image onto a set of oriented basis kernels. The components of the signature form an over-complete set of algebraic invariants, but are chosen to avoid instabilities associated with previously developed algebraic invariants. We demonstrate the use of this signature for representing and classifying junctions in grayscale imagery.

Original languageEnglish (US)
Pages185-188
Number of pages4
StatePublished - 1996
EventProceedings of the 1996 IEEE International Conference on Image Processing, ICIP'96. Part 2 (of 3) - Lausanne, Switz
Duration: Sep 16 1996Sep 19 1996

Other

OtherProceedings of the 1996 IEEE International Conference on Image Processing, ICIP'96. Part 2 (of 3)
CityLausanne, Switz
Period9/16/969/19/96

ASJC Scopus subject areas

  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Simoncelli, E. P. (1996). Rotation-invariant pattern signature. 185-188. Paper presented at Proceedings of the 1996 IEEE International Conference on Image Processing, ICIP'96. Part 2 (of 3), Lausanne, Switz, .