Recomposition and Retargeting of Photographic Images
Date Issued
2015
Date
2015
Author(s)
Chang, Hui-Tang
Abstract
With the goal of improving image aesthetics, we propose a novel approach for performing joint recomposition and retargeting of photographic images (R2P). Based on a reference image of interest, we aim at automatically altering the composition of the input source image, while the recomposed output will be jointly retargeted to fit the reference accordingly. Different from existing approaches which utilize pre-determined rules for improving image aesthetics, we only require one source-reference image pair as the input. Our R2P is achieved by recomposing the visual components of the source image via graph matching, followed by solving a constrained mesh-warping based optimization problem for retargeting. As a result, the recomposed output image would fit the reference while suppressing possible distortion. Our experiments confirm that our method is able to achieve visually satisfactory results, without the need to use pre-collected labeled data or predetermined aesthetics rules.
Subjects
Photography composition
graph matching
image aesthetics
computational photography
Type
thesis
File(s)![Thumbnail Image]()
Loading...
Name
ntu-104-R02921089-1.pdf
Size
23.32 KB
Format
Adobe PDF
Checksum
(MD5):29acf503c4e88e010f86f023088bdf64