English

A generalised feature for low level vision

Computer Vision and Pattern Recognition 2021-02-04 v1

Abstract

This papers presents a novel quantised transform (the Sinclair-Town or ST transform for short) that subsumes the rolls of both edge-detector, MSER style region detector and corner detector. The transform is similar to the unsharpunsharp transform but the difference from the local mean is quantised to 3 values (dark-neutral-light). The transform naturally leads to the definition of an appropriate local scale. A range of methods for extracting shape features form the transformed image are presented. The generalized feature provides a robust basis for establishing correspondence between images. The transform readily admits more complicated kernel behaviour including multi-scale and asymmetric elements to prefer shorter scale or oriented local features.

Keywords

Cite

@article{arxiv.2102.02000,
  title  = {A generalised feature for low level vision},
  author = {Dr David Sinclair and Dr Christopher Town},
  journal= {arXiv preprint arXiv:2102.02000},
  year   = {2021}
}

Comments

12 pages 8 figure

R2 v1 2026-06-23T22:47:49.318Z