Title :
An effective method for removing large object
Author :
Ma, Wenjuan ; Ma, Qinghua
Author_Institution :
Math. & Phys. Dept., Anhui Univ. of Sci. & Technol., Huainan, China
Abstract :
In this paper, we introduce a novel algorithm for digital inpainting of still images. The problem of image inpainting based on single image and its restoration is proposed. The distortion of images are rectification first dividing all images into different scene planar regions and dismisses the projective distortion, thus the visible information can be directly used. The new problem of image inpainting is how to use the wrapped images to repair reasonably the structure and texture information in the target part of the image. Then a new inpainting algorithm based on a pyramid approach to sub-pixel image fusion based on mutual information is applied to fill the holes. The experiment shows good and harmonious results for the repaired image. Our theory also develops the techniques of image fusion and makes it more practically.
Keywords :
image fusion; image restoration; image texture; digital inpainting; image distortion; image inpainting; image restoration; large object removal; mutual information; projective distortion; pyramid approach; scene planar regions; still images; structure information; subpixel image fusion; texture information; Histograms; Image fusion; Image restoration; Interpolation; Maintenance engineering; Mutual information; Presses; formatting; insert; style; styling;
Conference_Titel :
Image and Signal Processing (CISP), 2011 4th International Congress on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4244-9304-3
DOI :
10.1109/CISP.2011.6099907