| 研究生: |
林筠禎 Lin, Yun-Chen |
|---|---|
| 論文名稱: |
基於輪廓生成佈局之不規則形狀圖像拼貼 Irregular-Shaped Image Collage with Contour-Based Layout Generation |
| 指導教授: |
李同益
Lee, Tong-Yee |
| 學位類別: |
碩士 Master |
| 系所名稱: |
電機資訊學院 - 資訊工程學系 Department of Computer Science and Information Engineering |
| 論文出版年: | 2021 |
| 畢業學年度: | 109 |
| 語文別: | 英文 |
| 論文頁數: | 54 |
| 中文關鍵詞: | 圖像拼貼 、資料視覺化 、佈局設計 、視覺美感 |
| 外文關鍵詞: | image collage, data visualization, layout design, visual aesthetics |
| 相關次數: | 點閱:136 下載:23 |
| 分享至: |
| 查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
圖像拼貼是一種常見的資料視覺化應用,透過調整影像大小和旋轉其角度,再對影像位置進行排列,形成一個新的影像組合,藉此讓使用者可以快速瀏覽資料集裡面的內容。多數的拼貼軟體僅提供使用者矩形、圓形等形狀較為單純的輪廓作為畫布的形狀,在視覺上較無藝術性。有的拼貼軟體雖然允許使用者以客製化的形狀當作畫布,但往往是藉由重疊圖像來達成輪廓的呈現,造成圖像內容的嚴重損失,且拼貼內部往往還是存有空隙。為了解決前述問題,本研究提出新的方法,依照輪廓的曲率和骨架等特徵分割畫布,設計出一個排版緊密的佈局,再根據圖像的前景物體和美感分數等資訊,找出最佳的配置組合,最終生成一張既能保留圖像重要內容,也能兼顧佈局美感的不規則形狀圖像拼貼。
Image collage is a common application of data visualization. By adjusting the size, rotation angle and position of images, a new image combination is formed, which allows users to quickly browse the images in the dataset. Most tools for collage generation only provides simple shapes such as rectangle and circle as the shape of canvas, which leads to the lack of visual artistry. Although some tools allow users to specify customized shape as the shape of canvas, they often form the contour by overlapping the images, causing significant information loss, and gaps may still exists between the images. In order to solve the aforementioned problems, we propose a new method which divides the canvas based on features of the contour such as curvature and skeleton, designs a compact layout, finds the optimal assignment based on foreground objects and aesthetic score of the images, and finally generates an irregular-shaped image collage that not only preserves the salient content of images, but also takes the visual aesthetics of layout into account.
[1] D. Stromi, "ShapeX," [Online]. Available: https://www.reasyze.com/shapex/.
[2] Z. Wu and K. Aizawa, "PicWall: Photo collage on-the-fly," 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2013, pp. 1-10, doi: 10.1109/APSIPA.2013.6694305.
[3] S. Liu, X. Wang, P. Li and J. Noh, "Trcollage: Efficient Image Collage Using Tree-Based Layer Reordering," 2017 International Conference on Virtual Reality and Visualization (ICVRV), 2017, pp. 454-455, doi: 10.1109/ICVRV.2017.00120.
[4] J. Fan, "Photo Layout with a Fast Evaluation Method and Genetic Algorithm," 2012 IEEE International Conference on Multimedia and Expo Workshops, 2012, pp. 308-313, doi: 10.1109/ICMEW.2012.59.
[5] X. Pan et al., "Content-Based Visual Summarization for Image Collections," in IEEE Transactions on Visualization and Computer Graphics, vol. 27, no. 4, pp. 2298-2312, 1 April 2021, doi: 10.1109/TVCG.2019.2948611.
[6] X. Han, C. Zhang, W. Lin, M. Xu, B. Sheng and T. Mei, "Tree-Based Visualization and Optimization for Image Collection," in IEEE Transactions on Cybernetics, vol. 46, no. 6, pp. 1286-1300, June 2016, doi: 10.1109/TCYB.2015.2448236.
[7] Z. Yu, L. Lu, Y. Guo, R. Fan, M. Liu and W. Wang, "Content-Aware Photo Collage Using Circle Packing," in IEEE Transactions on Visualization and Computer Graphics, vol. 20, no. 2, pp. 182-195, Feb. 2014, doi: 10.1109/TVCG.2013.106.
[8] Luo, L., Shen, C., Liu, X., & Zhang, C. (2015). A Computational Model of the Short-Cut Rule for 2D Shape Decomposition. IEEE Transactions on Image Processing, 24, 273-283.
[9] Redmon, Joseph & Divvala, Santosh & Girshick, Ross & Farhadi, Ali. (2016). You Only Look Once: Unified, Real-Time Object Detection. 779-788. 10.1109/CVPR.2016.91.
[10] Redmon, Joseph & Farhadi, Ali. (2018). YOLOv3: An Incremental Improvement.
[11] Y. Kao, C. Wang and K. Huang, "Visual aesthetic quality assessment with a regression model," 2015 IEEE International Conference on Image Processing (ICIP), 2015, pp. 1583-1587, doi: 10.1109/ICIP.2015.7351067.
[12] X. Lu, Z. Lin, H. Jin, J. Yang and J. Z. Wang, "Rating Image Aesthetics Using Deep Learning," in IEEE Transactions on Multimedia, vol. 17, no. 11, pp. 2021-2034, Nov. 2015, doi: 10.1109/TMM.2015.2477040.
[13] Talebi, H., & Milanfar, P. (2018). NIMA: Neural Image Assessment. IEEE Transactions on Image Processing, 27, 3998-4011.
[14] He, Yuchen & Kang, Sung & Alvarez, Luis. (2021). Finding the Skeleton of 2D Shape and Contours: Implementation of Hamilton-Jacobi Skeleton. Image Processing On Line. 11. 18-36. 10.5201/ipol.2021.296.
[15] Shai Avidan and Ariel Shamir. 2007. Seam carving for content-aware image resizing. In ACM SIGGRAPH 2007 papers (SIGGRAPH '07). Association for Computing Machinery, New York, NY, USA, 10–es. DOI:https://doi.org/10.1145/1275808.1276390
[16] V. Cheung, "Shape Collage," [Online]. Available: http://www.shapecollage.com/.
[17] "FigrCollage," [Online]. Available: https://www.figrcollage.com/.