臺灣博碩士論文加值系統

在攜帶式裝置上，點陣格式的漫畫在縮放時會導致漫畫的品質降低。雖然將漫畫以轉換為向量形式可以避免此問題，向量漫畫有較大的檔案大小及較慢的顯像速度。我們提出一個以SVG格式為基礎的壓縮方法，能在將點陣漫畫轉換為SVG時，降低轉換後的檔案大小及顯像時間。我們先使用材質分割技術將漫畫分為材質與非材質區域，接著在將圖像轉換為SVG時將材質區域以SVG中的<Pattern>元素儲存來達到效果。在材質分割時我們使用CSGV(Composite sub-band Gradient Vector)作為特徵值，以SVM(Support Vector Machine)分類漫畫中的每個區域。再使用基於KL (Kullback-Leibler)距離及Split-Bregman方法進行演算的動態輪廓模組來增加分割準確率。我們對此方法以若干合成的漫畫進行實驗。實驗結果顯示此方法能讓向量漫畫在攜帶型裝置上達到更高的品質與效能。處理過的SVG圖檔，平均能減少55.3%的檔案大小及61.37%的顯示時間。此外，這方法也同時能使用在內含複數材質的漫畫上。

In portable device, scaling raster manga would result in reduced manga quality. Although converting manga into vector format could avoid this problem, vector manga has larger file size and slower rendering speed. We present a compression method based on SVG format, which can reduce file size and rendering time when converting raster manga into SVG format. We first use texture segmentation techniques to partition manga into texture segments and non-texture segment, then we use <pattern> element to store texture segments when converting manga. In image segmentation, we use Composite Sub-band Gradient Vector as texture descriptor and use Support Vector Machine to classify every area in manga. Then we use Active Contour Model, which based on KL (Kullback-Leibler) distance and Split-Bregman method, to enhance accuracy of segmentation. We conduct some experiments using several manga to test this method. Result shows this method can let vectorized manga have higher performance on portable device. In average, Segmentation accuracy is 93.3%, reduced file size is 55.3% and reduced rendering time is 61.37%. In addition, this method can also be applied on manga with multiple textures.

口試委員會審定書 #
誌謝 ii
中文摘要 iii
ABSTRACT iv
CONTENTS v
圖目錄 viii
表格目錄 x
Chapter 1 緒論 1
1.1 研究背景 1
1.2 研究目的 2
1.3 論文架構 3
Chapter 2 相關技術 4
2.1 複合子頻帶梯度向量 4
2.2 單類別支持向量機器 6
2.3 利用動態輪廓模型的快速材質分割 7
2.3.1 Texture Descriptor 8
2.3.2 動態輪廓模型 9
2.3.3 快速演算法 10
2.4 可縮放向量圖形 11
Chapter 3 研究方法 14
3.1 材質分類 15
3.1.1 材質的分類 16
3.1.2 分類器的訓練 16
3.1.3 像素分類 16
3.1.4 取樣參數的選擇 18
3.2 分割結果的優化 19
3.2.1 使用形態學的優化 20
3.2.2 使用動態輪廓模型的優化 21
3.3 動態輪廓模型的參數選擇 23
3.3.1 μ與λ值與準確率的關係 23
3.3.2 t與λ值與準確率的關係 26
3.4 漫畫的向量化及壓縮 26
Chapter 4 實驗結果與討論 28
4.1 材質分割結果 32
4.1.1 非固定參數的分割結果 32
4.1.2 固定參數的分割結果 32
4.1.3 複數材質的分割結果 33
4.2 壓縮效果 34
4.3 顯示速度的提升 37
4.3.1 電腦上的顯示速度 37
4.3.2 手機上的顯示速度 37
4.4 視覺效果 38
Chapter 5 結論與未來展望 43
附錄 44
壓縮前後的檔案大小 44
壓縮前後在電腦上的顯示時間 45
壓縮前後在手機上的顯示時間 46
REFERENCES 47

[1]落合早苗, 電子書籍&;#12499;&;#12472;&;#12493;&;#12473;調&;#26619;報告書2012: 株式&;#20250;社&;#12452;&;#12531;&;#12503;&;#12524;&;#12473;R&;D, 2012.
[2]高木利宏, 電子&;#12467;&;#12511;&;#12483;&;#12463;&;#12499;&;#12472;&;#12493;&;#12473;調&;#26619;報告書2010: 株式&;#20250;社&;#12452;&;#12531;&;#12503;&;#12524;&;#12473;R&;D, 2010.
[3]R.-I. Chang, Y. Yen, and T.-Y. Hsu, "An XML-based comic image compression," in Advances in Multimedia Information Processing-PCM 2008, ed: Springer, 2008, pp. 563-572.
[4]K. Kawamura, Y. Yamamoto, and H. Watanabe, "Gradation approximation for vector based compression of comic images," in Image Processing, 2005. ICIP 2005. IEEE International Conference on, 2005, pp. III-489-92.
[5]P. Huang, S. Dai, and P. Lin, "Texture image retrieval and image segmentation using composite sub-band gradient vectors," Journal of Visual Communication and Image Representation, vol. 17, pp. 947-957, 2006.
[6]V. Manian and R. Vasquez, "Scaled and rotated texture classification using a class of basis functions," Pattern Recognition, vol. 31, pp. 1937-1948, 1998.
[7]N. Dalal and B. Triggs, "Histograms of oriented gradients for human detection," in Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, 2005, pp. 886-893.
[8]B. Scholkopf, J. C. Platt, J. Shawe-Taylor, A. J. Smola, and R. C. Williamson, "Estimating the support of a high-dimensional distribution," Neural computation, vol. 13, pp. 1443-1471, 2001.
[9]N. Houhou, J.-P. Thiran, and X. Bresson, "Fast Texture Segmentation Based on Semi-Local Region Descriptor and Active Contour," Numerical Mathematics: Theory, Methods &; Applications, vol. 2, 2009.
[10]T. Goldstein, X. Bresson, and S. Osher, "Geometric applications of the split Bregman method: segmentation and surface reconstruction," Journal of Scientific Computing, vol. 45, pp. 272-293, 2010.
[11]N. Houhou, J. Thiran, and X. Bresson, "Fast texture segmentation model based on the shape operator and active contour," in Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on, 2008, pp. 1-8.
[12]X. Bresson. Image &; Learning codes. Available: https://googledrive.com/host/0B3BTLeCYLunCc1o4YzV1Ui1SeVE/codes.html
[13]G. Aubert, M. Barlaud, O. Faugeras, and S. Jehan-Besson, "Image segmentation using active contours: Calculus of variations or shape gradients?," SIAM Journal on Applied Mathematics, vol. 63, pp. 2128-2154, 2003.
[14]S. Jehan-Besson, M. Barlaud, and G. Aubert, "DREAM2S: Deformable regions driven by an eulerian accurate minimization method for image and video segmentation," International Journal of Computer Vision, vol. 53, pp. 45-70, 2003.
[15]X. Bresson, S. Esedo&;#7713;lu, P. Vandergheynst, J.-P. Thiran, and S. Osher, "Fast global minimization of the active contour/snake model," Journal of Mathematical Imaging and vision, vol. 28, pp. 151-167, 2007.
[16]T. F. Chan, S. Esedoglu, and M. Nikolova, "Algorithms for finding global minimizers of image segmentation and denoising models," SIAM Journal on Applied Mathematics, vol. 66, pp. 1632-1648, 2006.
[17]M. Weber. Autotrace. Available: http://autotrace.sourceforge.net/
[18]E. Dahlstrom, P. Dengler, A. Grasso, C. Lilley, C. McCormack, D. Schepers, et al. Scalable Vector Graphics (SVG) 1.1 (Second Edition ed.). Available: http://www.w3.org/TR/SVG11/
[19]C. Cortes and V. Vapnik, "Support-vector networks," Machine learning, vol. 20, pp. 273-297, 1995.
[20]C.-C. Chang and C.-J. Lin, "LIBSVM: a library for support vector machines," ACM Transactions on Intelligent Systems and Technology (TIST), vol. 2, p. 27, 2011.
[21]Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, "Image quality assessment: from error visibility to structural similarity," Image Processing, IEEE Transactions on, vol. 13, pp. 600-612, 2004.