Title :
Retrospective illumination correction of retinal fundus images from gradient distribution sparsity
Author :
Zheng, Yuanjie ; Vanderbeek, Brian ; Xiao, Rui ; Daniel, Ebenezer ; Stambolian, Dwight ; Maguire, Maureen ; O´Brien, Joan ; Gee, James
Author_Institution :
Dept. of Radiol., Univ. of Pennsylvania, Philadelphia, PA, USA
Abstract :
We present a novel technique for retrospective illumination correction of retinal fundus images from the sparsity property of image gradient distribution. It can automatically estimate the illumination inhomogeneity given an arbitrary retinal fundus image. Experimental results on 665 high resolution fundus images show both the efficiency of our algorithm on illumination correction and its high value on improving the accuracy of blood-vessel segmentation.
Keywords :
biomedical optical imaging; blood; blood vessels; eye; gradient methods; image resolution; image segmentation; medical image processing; arbitrary retinal fundus image; blood-vessel segmentation; gradient distribution sparsity; high-resolution fundus images; image gradient distribution; retrospective illumination correction; Biomedical imaging; Image resolution; Image segmentation; Lighting; Nonhomogeneous media; Retina;
Conference_Titel :
Biomedical Imaging (ISBI), 2012 9th IEEE International Symposium on
Conference_Location :
Barcelona
Print_ISBN :
978-1-4577-1857-1
DOI :
10.1109/ISBI.2012.6235719
