Album Quickview in Comic-like Layout via Quartet Analysis


Zhibin Zheng, Yan Zhang, Miao Zheng, Zhengxing Sun

Short paper, accepted to Pacific Graphics(2014) Conference (Proc. PG 2014)



For clear summary and efficient search of images for album, which carries a story of life record, we propose a new approach for quickview of album in comic-like layout via quartet analysis. How to organize the images in album and in what way to display images in collage are two key problems for album quickview. For the first problem, we take the idea of model organization method based on quartet analysis to construct categorization tree to organize the images; while for the second problem, we utilize the topological structure of categorization tree to decompose it into multiple groups of images and extract representative image from each group for subsequent collage. For the collage part, we choose comic-like layout to present collage because comic provides a concise way for storytelling and it has variablitiy in layout styles, which is suitable for album summary. Experiments demonstrate that our method could organize the images effectively and present images in collage with diverse styles as well.

Overview


An overview of our approach. With an input album(left image), we first organize them into a classification tree with hierarchical structure(middle image), and then display the summary of the album in a comic-like layout style.



Evaluation


We compare our results with [RBHB06] and [YLG*14], shown as bellow. The left result is from [RBHB06], the middle result is from [YLG*14] and the right result is ours





Other Results


Our results for other albums.





PAPER: Album Quickview in Comic-like Layout via Quartet Analysis

[RBHB06]ROTHER C., BORDEAUX L., HAMADI Y., BLAKEA.: Autocollage. ACM Trans. Graph. 25, 3 (July 2006), 847–852. http://research.microsoft.com/en-us/um/people/ablake/papers/ablake/Rother_Siggraph06.pdf


[YLG*14]YU Z., LU L., GUO Y., FAN R., LIU M., WANG W.:Content-aware photo collage using circle packing. IEEE Transactions on Visualization and Computer Graphics 20, 2 (2014),182–195. http://cs.nju.edu.cn/ywguo/PhotoCollage/Index.html