DocumentCode :
3403042
Title :
Image inpainting based on pyramids
Author :
Farid, M. Shahid ; Khan, Hassan ; Mahmood, Arif
Author_Institution :
Punjab Univ. Coll. of Inf. Technol., Univ. of the Punjab, Lahore, Pakistan
fYear :
2010
fDate :
24-28 Oct. 2010
Firstpage :
711
Lastpage :
715
Abstract :
Image inpainting is a technique used to automatically recover the damaged or missing regions in digital images or used to remove the unwanted objects from images. This paper presents a novel approach for recovering the damaged regions of digital images based on pyramids. The idea is to generate the pyramids of the image to the level where all the damaged pixels are fully eliminated. Then the damaged pixels are filled in from the bottom pyramid to the top. In pyramid image at level i, the damaged pixels are filled in from the EXPANDED pyramid image at level i -1, and so on up to the level 0 pyramid. The proposed technique has been tested over a large verity of images and shown excellent results to restore small damaged regions and satisfactory results for large damaged regions.
Keywords :
image restoration; damaged pixel; damaged region; digital image; image inpainting; image restoration; image retouch; image scratch removal; missing region; pyramid image; unwanted object; Image edge detection; Image restoration; Mathematical model; Pixel; Signal to noise ratio; TV; Image Inpainting; Image Restoration; Image Retouch; Image Scratch Removal;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Signal Processing (ICSP), 2010 IEEE 10th International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-5897-4
Type :
conf
DOI :
10.1109/ICOSP.2010.5655758
Filename :
5655758
Link To Document :
بازگشت