International Journal of Computer Vision

, Volume 23, Issue 1, pp 45–78

SUSAN—A New Approach to Low Level Image Processing

Authors

  • Stephen M. Smith
  • J. Michael Brady
Article

DOI: 10.1023/A:1007963824710

Cite this article as:
Smith, S.M. & Brady, J.M. International Journal of Computer Vision (1997) 23: 45. doi:10.1023/A:1007963824710

Abstract

This paper describes a new approach to low level image processing; in particular, edge and corner detection and structure preserving noise reduction.

Non-linear filtering is used to define which parts of the image are closely related to each individual pixel; each pixel has associated with it a local image region which is of similar brightness to that pixel. The new feature detectors are based on the minimization of this local image region, and the noise reduction method uses this region as the smoothing neighbourhood. The resulting methods are accurate, noise resistant and fast.

Details of the new feature detectors and of the new noise reduction method are described, along with test results.

Copyright information

© Kluwer Academic Publishers 1997