隨著文字雲的發明，人們能從輕易的從大量文本資料中擷取重要且珍貴的訊息，但文字雲僅能針對文本資料作分析，對於影像是束手無策，於是影像雲這一概念在近幾年漸漸開始被廣泛的討論。
現有的影像雲之影像形狀，都還是以矩形為主在做處理，使得影像彼此之間存在有過多的空隙；而以拼貼為主的影像拼貼技術，雖然能夠做到近乎完美、空隙極小的拼貼成果，但在運算時間的層面上卻總是過於冗長。
本篇論文將會結合上述影像雲與影像拼貼的優點，提出一種嶄新的資料視覺化形式：靜態的影像形狀拼貼與動態的時變之影像形狀雲。在影像拼貼的過程中，利用矩形的特性，將計算二維的時間複雜度降為一維的時間複雜度，在加速拼貼之餘同時保持影像的形狀；在時變之影像雲中，使用剛體動力學，利用大量的約束來模擬並將這些具有時變性的影像形狀排列成特定的外形。每一個影像形狀都會被視為是一個剛體，而不同的約束則能調整影像雲的結構，使其更加的緊密、有美感。最後，兩者的結果都會再利用變形的技術來更進一步的縮小整理的空隙。與之前的方法相比，我們所提之新方法，利用影像雲（文字雲）計算時間快速之優勢，彌補影像拼貼在運算層面上的劣勢；也利用影像拼貼空隙極小之特性，補足影像雲在做矩形處理結合時，空隙過大之缺點，在結果呈現與計算時間複雜度之間取得了極佳的平衡。

As word cloud is invented, people can get the important information easily from a great deal of text data. However, word cloud is only for text data. It’s useless for image data. Therefore, the concept of image cloud has started to be discussed for these years.
The image shape for image cloud now is mainly based on rectangle to be handled, which leads to lots of gaps between images. As for the collage technology of largely based on painting, it can create a gap-less and near-perfect collage result, but it takes tons of time in its calculation time.
This thesis combines those advantages in both of image cloud and image collage, and propose a brand-new structure of data visualization: static image shape collage and dynamic time-varying image shape cloud. We exploit the characteristic of rectangle to decrease the time complexity from two dimension to one dimension, which can keep image shapes during acceleration. In time-varying image shape cloud, we use rigid body dynamics with multiple constraints to simulate, and let those image shapes with time-varying characteristic arrange in a special shape. Every image shape is regarded as a rigid body. Then Each constraint can adjust the structure of image shape collage, so that animation results will be closer to image shape collage. In contrast to the state-of-the-art work, the method we propose uses the advantage of fast calculation time in word cloud to make up for the disadvantage of one in image shape collage, and then makes use of the characteristic of less gaps in image shape collage to atone for the disadvantage of considerable gaps during rectangle calculation in image cloud. We get a great balance between results and calculation time complexity.

Reference

[1] F. B. Viegas, M. Watternberg and J. Feinberg, "Participatory Visualization with Wordle," IEEE Trans. Vis. Comput. Graph., pp. 1137-1144, 11 2009.
[2] H. Strobelt, M. Spicker, A. Stoffel, D. Keim and O. Deussen, "Rolled-outWordles: A Heuristic Method for Overlap Removal of 2D Data Representatives," Comput. Graph. Forum, pp. 1135-1144, 2012.
[3] K. Koh, B. Lee, B. Kim and J. Seo, "ManiWordle: Providing Flexible Control over Wordle," IEEE Trans. Vis. Comput. Graph., pp. 1190-1197, 11-12 2010.
[4] H. Strobelt, D. Oelke, C. Rohrdantz, A. Stoffel, D. A. Keim and O. Deussen, "Document Cards: A Top Trumps Visualization for Documents," IEEE Trans. Vis. Comput. Graph., pp. 1145-1152, 11-12 2009.
[5] S. Afzal, R. Maciejewski, Y. Jang, N. Elmqvist and D. S. Ebert, "Spatial Text Visualization Using Automatic Typographic Maps," IEEE Trans. Vis. Comput. Graph., pp. 2556-2564, 12 2012.
[6] R. Maharik, M. Bessmeltsev, A. Sheffer, A. Shamir and N. Carr, "Digital Micrography," ACM Trans. Graph., pp. 100:1-100:12, 12 2011.
[7] S. Havre, B. Hetzler and L. Nowell, "ThemeRiver: Visualizing Theme Changes over Time," IEEE Symp. Inform. Vis., pp. 115-123, 2000.
[8] L. Shi, F. Wei, S. Liu, L. Tan, X. Lia and M. X. Zhou, "Understanding Text Corpora with Multiple Facets," Proc. IEEE Symp. Visual Analytics Sci. Technol., pp. 99-106, 2010.
[9] C. Collins, F. B. Viegas and M. Wattenberg, "Parallel Tag Clouds to Explore and Analyze Faceted Text Corpora," Proc. IEEE Symp. Visual Analytics Sci. Technol., pp. 91-98, 2009.
[10] C. Culy, V. Lyding and H. Dittmann, "Structured Parallel Coordinates: a visualization for analyzing structured language data," Proc. 3rd Int. Conf. Corpus Linguistics, pp. 6-9, 2011.
[11] B. Lee, N. H. Riche, A. K. Karlson and S. Carpendale, "SparkClouds: Visualizing Trends in Tag Clouds," IEEE Trans. Vis. Comput. Graph., pp. 1182-1189, 11 2010.
[12] W. Cui, Y. Wu, S. Liu, F. Wei, M. X. Zhou and H. Qu, "Context Preserving Dynamic Word Cloud Visualization," IEEE Comput. Graph. Appl., pp. 42-53, 11-12 2010.
[13] M.-T. Chi, S.-S. Lin, S.-Y. Chen, C.-H. Lin and T.-Y. Lee, "Morphable Word Clouds for Time-Varying Text Data Visualization," IEEE Trans. Vis. Comput. Graph., 12 2015.
[14] D. Heesch, "A survey of browsing models for content based image retrieval," Multimedia Tools and Applications, pp. 261-284, 2008.
[15] W. Plant and G. Schaefer, "Visualisation and Browsing of Image Databases," in Multimedia Analysis, Processing and Communications, Springer Berlin Heidelberg, 2011, pp. 3-57.
[16] T. J. Kelly and K.-L. Ma, "MoireGraphs: Radial Focus+Context Visualization and Interaction for Graphs with Visual Nodes," INFOIVS, pp. 59-66, 2003.
[17] G. Strong and M. Gong, "Self-Sorting Map: An Efficient Algorithm for Presenting Multimedia Data in Structured Layouts," IEEE Trans. Multimedia, 2014.
[18] K. Schoeffmann, D. Ahlström and M. A. Hudelist, "3-D Interfaces to Improve the Performance of Visual Known-Item Search," IEEE Trans. Multimedia, pp. 1942-1951, 2014.
[19] M. Dubinko, R. Kumar, J. Magnani, J. Novak, P. Raghavan and A. Tomkins, "Visualizing Tags over Time," ACM Trans. Web, 2007.
[20] X. Han, C. Zhang, W. Lin, M. Xu, B. Sheng and T. Mei, "Tree-based Visualization and Optimization for Image Collection," IEEE Transactions on Cybernetics, 6 2016.
[21] T. Liu, J. Wang, J. Sun, N. Zheng, X. Tang and H.-Y. Shum, "Picture Collage," IEEE Trans. Multimedia, pp. 1225-1239, 2009.
[22] M. H. Lee, N. Singhal, S. Cho and I. K. Park, "Mobile Photo Collage," IEEE Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 24-30, 2010.
[23] Y.-M. Kuo, H.-K. Chu, M.-T. Chi, R.-R. Lee and T.-Y. Lee, "Generating Ambiguous Figure-Ground Images," IEEE Trans. Vis. Comput. Graph., pp. 1534-1545, 5 2017.
[24] K. C. Kwan, L. T. Sinn, C. Han, T.-T. Wong and C.-W. Fu, "Pyramid of Arclength Descriptor for Generating Collage of Shapes," ACM Trans. Graph., 11 2016.
[25] B. Reinert, T. Ritschel and H.-P. Seidel, "Interactive By-example Design of Artistic Packing Layouts," SIGGRAPH Asia, 2013.
[26] H. Averbuch-Elor, D. Cohen-Or and J. Kopf, "Smooth Image Sequences for Data-driven Morphing," Computer Graphics Forum, (Proceedings Eurographics 2016), 2016.
[27] N. Liu, J. Han and M.-H. Yang, "PiCANet: Learning Pixel-wise Contextual Attention for Saliency Detection," Computer Vision and Pattern Recognition, 21 8 2017.
[28] Q. Yan, L. Xu, J. Shi and . J. Jia, "Hierarchical Saliency Detection," IEEE Computer Vision and Pattern Recognition (CVPR), 2013.
[29] J. Shi, Q. Yan, L. Xu and J. Jia, "Hierarchical Image Saliency Detection on Extended CSSD," IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), 2016.
[30] G. Li and Y. Yu, "Deep Contrast Learning for Salient Object Detection," IEEE Computer Vision and Pattern Recognition (CVPR), 6 2016.
[31] G. Li and Y. Yu, "Visual Saliency Based on Multiscale Deep Features," IEEE Computer Vision and Pattern Recognition (CVPR), 6 2015.
[32] G. Li and Y. Yu, "Visual Saliency Detection Based on Multiscale Deep CNN Features," IEEE Trans. Image Processing (TIP), pp. 5012-5024, 2016.
[33] M.-M. Cheng, N. J. Mitra, X. Huang, P. H. S. Torr and S.-M. Hu, "Global Contrast based Salient Region Detection," IEEE TPAMI, pp. 569-582, 2015.
[34] S. Suzuki and others, "Topological structural analysis of digitized binary images by border following," Computer Vision, Graphics, and Image Processing, pp. 32-46, 1985.
[35] Z. Deng, X. Hu, L. Zhu, X. Xu, J. Qin, G. Han and P.-A. Heng, "R3Net: Recurrent Residual Refinement Network for Saliency Detection," IJCAI, 2018.