UCL logo

UCL Discovery

UCL home » Library Services » Electronic resources » UCL Discovery

Dynamic histogram warping of image pairs for constant image brightness

Cox, IJ; Roy, S; Hingorani, SL; (1996) Dynamic histogram warping of image pairs for constant image brightness. In: IEEE International Conference on Image Processing. (pp. 366 - 369).

Full text not available from this repository.

Abstract

An examination of the images contained in the SRI JISCT stereo database revealed that the constant image brightness assumption in computer vision is often false. In this paper, experimental results show that image histograms are closely matched after dynamic histogram warping (DHW), especially when both histograms are modified simultaneously. DHW is also capable of removing simple constant additive and multiplicative biases without derivative operations, thereby avoiding amplification of high frequency noise. It is demonstrated that DHW can improve the estimates from stereo and optical flow estimators.

Type:Proceedings paper
Title:Dynamic histogram warping of image pairs for constant image brightness
UCL classification:UCL > School of BEAMS > Faculty of Engineering Science > Computer Science

Archive Staff Only: edit this record