Title :
A segmentation method for spotted-partten damaged Thangka image combining grayscale morphology with maximum entropy threshold
Author :
Baojuan Luo ; Weilan Wang ; Yanjun Jia ; Wanpin Gao
Author_Institution :
Coll. of Math & Comput. Sci., Northwest Univ. for Nat., Lanzhou, China
Abstract :
Before inpainting damaged Thangka image using digital technology, it´s necessary to segment the damaged regions. A segmentation algorithm is proposed to segment the spotted regions of damaged Thangka mage, which combines grayscale morphology with maximum entropy threshold method. First of all, the mathematical morphology is used to act on RGB channels respectively in order to segment the tiny spots. Afterwards, maximum entropy threshold method is applied to segment the large spots. Finally, the above results are merged. The final segmentation result is achieved. Experimental results demonstrate the effectiveness of the proposed algorithm.
Keywords :
image colour analysis; image reconstruction; image segmentation; maximum entropy methods; RGB channels; damaged regions; digital technology; grayscale morphology; inpainting damaged Thangka image; mathematical morphology; maximum entropy threshold method; segmentation algorithm; segmentation method; spotted regions; spotted-partten damaged Thangka image; Clustering algorithms; Computers; Educational institutions; Entropy; Gray-scale; Image segmentation; Morphology; Thangka; damaged regions segmentation; grayscale morphology; maximum entropy threshold method;
Conference_Titel :
Image and Signal Processing (CISP), 2013 6th International Congress on
Conference_Location :
Hangzhou
Print_ISBN :
978-1-4799-2763-0
DOI :
10.1109/CISP.2013.6744060
