Title :
Contour-Preserved Retargeting of Cartoon Images
Author :
Xing Gao ; Jing Liu ; Juncong Lin ; Minghong Liao ; Lisheng Xiang
Author_Institution :
Software Sch., Xiamen Univ., Xiamen, China
Abstract :
Mobile comic is now evolving into an industry with great potential for its convenience, huge user base etc. A key challenge in mobile comic is to adapt the comic content to various mobile screens for better visual effect, which is also called image retargeting. Although a lot of works have been conducted in this area, most of them target on nature or natural-like images. However, cartoon images are quite different from natural images, they are usually depicted by contour curves, and colored uniformly or with simple pattern. These unique characteristics make existing methods not suitable for comic contents. In this paper, we presented a content-aware retargeting method targeting on cartoon images. We focus on effectively preservation of those contours in cartoon images due to their dominant effect in depicting the content. Our method does not need explicit computation of an importance map. The experimental results shows that our method outperforms other methods on cartoon images.
Keywords :
image colour analysis; mobile computing; comic content; content-aware retargeting method; contour curves; contour-preserved cartoon image retargeting; image retargeting; importance map; mobile comic; mobile screens; natural-like images; visual effect; Educational institutions; Electronic mail; Feature extraction; Image edge detection; Mobile communication; Shape; Software; Cartoon image retargeting; Contour-preserved; Mesh warping;
Conference_Titel :
Computational Science and Engineering (CSE), 2014 IEEE 17th International Conference on
Conference_Location :
Chengdu
Print_ISBN :
978-1-4799-7980-6
DOI :
10.1109/CSE.2014.325