A new correlation criterion based on gradient fields similarity
- 1 January 1996
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 632-636 vol.1
- https://doi.org/10.1109/icpr.1996.546101
Abstract
Correlation based methods are a common tool for the correspondence problem. They are able to perform a dense point-to-point matching between two images, but post-processing is often necessary to improve the results. In this paper we propose a new correlation measure using the gradient vector fields of the images. We compare our method to classical correlation measures based on the grey levels. The new method gives better results than others when it is applied on random dot stereograms and on real images.Keywords
This publication has 8 references indexed in Scilit:
- Surface reconstruction directly from binocular stereo images by multiscale-multistage regularizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Matching images by comparing their gradient fieldsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Automatic feature point extraction and tracking in image sequences for arbitrary camera motionInternational Journal of Computer Vision, 1995
- Local stereoscopic depth estimationImage and Vision Computing, 1994
- An optimal linear operator for step edge detectionCVGIP: Graphical Models and Image Processing, 1992
- Vertical and horizontal disparities from phaseImage and Vision Computing, 1991
- Using Local Orientational Information As Image Primitive For Robust Object RecognitionPublished by SPIE-Intl Soc Optical Eng ,1989
- Efficient registration of stereo images by matching graph descriptions of edge segmentsInternational Journal of Computer Vision, 1987