期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2017
卷号：6
期号：5
页码：8806
DOI：10.15680/IJIRSET.2017.0605255
出版社：S&S Publications
摘要：Image Mosaicking have found a vast field of applications ranging from satellite or aerial imagery tomedical imaging street view maps, city 3D modelling, texture synthesis or stereo reconstruction and so on. This paperproposes a probabilistic color correction algorithm for correcting the photometrical disparities. First, the image to becolor corrected is segmented into several regions using mean shift. Then, connected regions are extracted using a regionfusion algorithm. Local joint image histograms of each region are modeled as collections of truncated Gaussians usinga maximum likelihood estimation procedure. Then, local color palette mapping functions are computed using these setsof Gaussians. The color correction is performed by applying those functions to all the regions of the image. A newcolor correction algorithm with the usage of truncated Gaussians is used to perform accurate color distribution. Resultsshow that the proposed approach obtains the best average scores in both data sets and evaluation metrics and is also themost robust to failures.
关键词：Color correction; image Mosaicking; color transfer; color palette mapping function.
