A pixel dissimilarity measure that is insensitive to image sampling
- 1 April 1998
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 20 (4) , 401-406
- https://doi.org/10.1109/34.677269
Abstract
Because of image sampling, traditional measures of pixel dissimilarity can assign a large value to two corresponding pixels in a stereo pair, even in the absence of noise and other degrading effects. We propose a measure of dissimilarity that is provably insensitive to sampling because it uses the linearly interpolated intensity functions surrounding the pixels. Experiments on real images show that our measure alleviates the problem of sampling with little additional computational overhead.Keywords
This publication has 12 references indexed in Scilit:
- A Bayesian treatment of the stereo correspondence problem using half-occluded regionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- A binocular stereo algorithm for reconstructing sloping, creased, and broken surfaces in the presence of half-occlusionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Matching images by comparing their gradient fieldsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Depth discontinuities by pixel-to-pixel stereoPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A Maximum Likelihood Stereo AlgorithmComputer Vision and Image Understanding, 1996
- A new correlation criterion based on gradient fields similarityPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1996
- Occlusions and binocular stereoInternational Journal of Computer Vision, 1995
- Non-parametric local transforms for computing visual correspondencePublished by Springer Nature ,1994
- Using Local Orientational Information As Image Primitive For Robust Object RecognitionPublished by SPIE-Intl Soc Optical Eng ,1989
- Practical Real-Time Imaging Stereo MatcherOptical Engineering, 1984