Matching images by comparing their gradient fields
- 17 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
We present a simple yet powerful method to performpoint-to-point matching between two images. Themethod uses an evidence measure, whose value for agiven displacement reflects both the similarity betweentwo locations and the confidence in a correct match.The measure is based on the gradient fields of the images,and can be computed quickly and in parallel.Accumulating the evidence measure for different displacementsallows (1) stable computation of correspondenceswithout smoothing across...Keywords
This publication has 7 references indexed in Scilit:
- Real-time binocular smooth pursuitInternational Journal of Computer Vision, 1993
- Fixation-based filteringPublished by SPIE-Intl Soc Optical Eng ,1992
- Using Local Orientational Information As Image Primitive For Robust Object RecognitionPublished by SPIE-Intl Soc Optical Eng ,1989
- A computational framework and an algorithm for the measurement of visual motionInternational Journal of Computer Vision, 1989
- Detection of binocular disparitiesBiological Cybernetics, 1985
- Computational StereoACM Computing Surveys, 1982
- Determining optical flowArtificial Intelligence, 1981