Title :
Shadow removal of single texture region using local histogram matching
Author :
Pan Xiao ; Yong Zhao ; Yule Yuan
Author_Institution :
Shenzhen Grad. Sch., Key Lab. of Integrated Microsyst., Peking Univ., Shenzhen, China
Abstract :
Shadows have long been a problem to computer vision algorithms. Removing shadow can significantly improve the performance of several vision task such as object detection and image segmentation. Various methods of shadow removal in images had been developed. In this paper, we discussed the characteristic of shadowed region with single texture statistically, based on an illumination model, and then developed a simple and fast way of removal shadow using local histogram matching in different illumination reduction level.
Keywords :
computer vision; image matching; image segmentation; image texture; object detection; computer vision algorithms; illumination reduction level; image segmentation; local histogram matching; object detection; shadow removal; single texture region; statistically analysis; Computer vision; Educational institutions; Gaussian distribution; Histograms; Image segmentation; Lighting; Reflectivity; histogram matching; ilumination model; shadow removal;
Conference_Titel :
Audio, Language and Image Processing (ICALIP), 2014 International Conference on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4799-3902-2
DOI :
10.1109/ICALIP.2014.7009877