簡易檢索 / 詳目顯示
| 研究生： |
許瀚仁 Hsu, Han-Jen |
|---|---|
| 論文名稱： |
物體分割與紋理合成用於影像和視訊處理之研究 A Research for Object Segmentation and Texture Synthesis in Image/Video Processing |
| 指導教授： |
王駿發
Wang, Jhing-Fa |
| 學位類別： |
博士 Doctor |
| 系所名稱： |
電機資訊學院 - 電機工程學系 Department of Electrical Engineering |
| 論文出版年： | 2008 |
| 畢業學年度： | 96 |
| 語文別： | 英文 |
| 論文頁數： | 85 |
| 中文關鍵詞： | 物體分割 、紋理合成 、區域填補 、視訊編碼 |
| 外文關鍵詞： | object segmentation, video coding, texture synthesis, region filling |
| 相關次數： | 點閱：105 下載：3 |
| 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 |
本研究包含三個部份：互動式物體分割與紋理合成用於影像和視訊處理。第一部份為互動式物體分割，可讓使用者能夠很方便及快速地將想要的物體從圖片中分割出來。使用者只需要在圖片上指定少量的前景和背景之種子，此演算法將根據這些資訊，將使用者所想要的物體分割出來。此演算法以分水嶺為基礎將影像切割成若干個區域，如此便可大大地降低計算時間，再利用使用者指定的前/背景區域，將剩餘區域分類成前景或背景以產生所需的物體。
第二部份為紋理合成用於影像處理方面，我們提出的區域填補演算法利用空間域與頻率域完成影像填補，包含紋理合成法、加權內插法與重新確認的方法。在填補的過程中，色彩紋理可以選擇填補的方法，以減少計算的時間及增加紋理合成的準確度。完成影像區域填補後，缺陷偵測技術可以驗證填補的品質，以決定是否需要再次填補。
第三部份為紋理合成用於視訊處理方面，可以用來改善以區塊為基礎的視訊編碼，首先在編碼端將輸入視訊資料作影像分割將畫面分為許多影像區塊，再將紋理部分的區塊萃取出來，分析紋理的特徵，在解碼端將所分析過之紋理部份合成，以對應到移除的部份，並輸出對應後的視訊資料。利用此方法可以改善現有H.264/AVC視訊編碼的壓縮率。
This research includes three parts: interactive object segmentation and texture synthesis in image/video processing. In the first part, interactive object segmentation is presented to allow the user extracting the wanted object rapidly and conveniently. The user only needs to indicate few foreground seeds and background seeds in the image. Our algorithm will extract the object according to this information. This algorithm is based on watershed algorithm to segment the image into many regions to decrease the computation time. The object will be extracted after region classification by using the indicated foreground regions and background regions.
The second part is texture synthesis for image processing. The proposed region-filling algorithm exploits the spatial domain and frequency domain to fill the removal region. The algorithm consists of a texture synthesis technique and a weighted interpolation method with a refinement approach. In the procedure of region-filling, color texture distribution analysis is used to choose whether the sub-patch texture synthesis technique or the weighted interpolation method should be applied. After region filling, artifact detection mechanism is used to verify the visual quality and then to decide if the output image will be re-filled.
The third part is texture synthesis in video processing to improve the block-based video coding. At first, the input video is segmented into many blocks in the encoder side. The regions belonged to texture are extracted to analyze the characteristic of texture. The regions are synthesized and mapped to the corresponding part in the decoder side. We use this approach to improve the compression ration of H.264/AVC video coding.
[1] H. J. Hsu, J. F. Wang, J. S. Lee, “Interactive Object Segmentation in Digital Images by Foreground/Background Region Classification with Hierarchical Queues,” Journal of the Chinese Institute of Engineers. (under review)
[2] J. F. Wang, H. J. Hsu, J. S. Lee, “Intelligent Object Extraction Algorithm based on Foreground/Background Classification,” International Symposium on Uniquitous Intelligence and Smart Worlds, 2005.
[3] Adobe Photoshop User Guide, ADOBE SYSTEMS INC., 2002.
[4] E. N. Mortensen, W. A. Barrett, “Toboggan-based intelligent scissors with a four parameter edge model,” in Proceedings of CVPR, 1999.
[5] M. Gleicher, “Image snapping,” in Proceedings of ACM SIGGRAPH, 1995.
[6] P. Perez, A. Blake, M. Gangent, “Jetstream: Probabilistic contour segmentation with particles,” in Proceedings of ICCV, 2001.
[7] Jian Sun, Jiaya Jia, Chi-Keung Tang, Heung-Yeung Shum, “Poisson matting,” ACM Transactions on Graphics, vol. 23, no. 3, 2004.
[8] C. Rother, V. Kolmogorov, A. Blake, “GrabCut-interactive foreground segmentation using iterated graph cuts,” ACM Transactions on Graphics, vol. 23, no. 3, 2004.
[9] Yin Li, Jian Sun, Chi-Keung Tang, Heung-Yeung Shum, “Lazy snapping,” ACM Transactions on Graphics, vol. 23, no. 3, 2004.
[10] Hai Gao, Wan-Chi Siu, Chao-Huan Hou, “Improved Techniques for Automatic Image Segmentation,” IEEE Trans. on Circuits and Systems for Video Technology, vol. 11, no. 12, pp. 1273 – 1280, 2001.
[11] J. M. Kasson, W. Plouffe, “An Analysis of Selected Computer Interchange Color Spaces,” ACM Trans. on Graphics, vol. 11, no. 4, pp. 373-405, 1992.
[12] Rafael C. Gonzalez, Richard E. Woods, Digital Image Processing, Reading, Prentice-Hall, Inc, 2002.
[13] D. J. Heeger and J. R. Bergen, “Pyramid-based texture analysis/synthesis,” in Proc. ACM Conf. Computer Graphics , Los Angeles, CA, 1995, vol. 29, pp. 229-233.
[14] J. Portilla and E. P. Simoncelli, “A parametric texture model based on joint statistics of complex wavelet coefficients,” Int’l J. Computer Vision, vol. 40, no. 1, pp. 49-71, Oct. 2000.
[15] A. Efros and T. Leung, “Texture synthesis by non-parametric sampling,” in Proc. Int. Conf. Computer Vision, Kerkyra, Greece, Sep. 1999, pp. 1033-1038.
[16] L. Y. Wei and M. Levoy, “Fast texture synthesis using tree-structured vector quantization,” in Proc. ACM Conf. Computer Graphics, Jul. 2000, pp. 479-488.
[17] M. Ashikhmin, “Synthesizing natural textures,” in Proc. ACM Symp. Interactive 3D Graphics, Mar. 2001, pp. 217-226.
[18] S. C. Pei, Y. C. Zeng, and C. H. Chang, “Virtual restoration of ancient Chinese paintings using color contrast enhancement and lacuna texture synthesis,” IEEE Trans. Image Processing, vol. 13, no. 3, pp. 416-429, 2004.
[19] A. Efros and W. T. Freeman, “Image quilting for texture synthesis and transfer,” in Proc. ACM Conf. Computer Graphics, Aug. 2001, pp. 341-346.
[20] L. Liang, C. Liu, Y. Q. Xu, B. Guo, and H. Y. Shum, “Real-time texture synthesis by patch-based sampling”, in ACM Trans. on Graphics, vol. 20, pp. 127-150, 2001.
[21] M. Bertalmio, G. Sapiro, V. Caselles, and C. Ballester, “Image inpainting,” in Proc. ACM Conf. Computer Graphics, Jul. 2000, pp. 417-424.
[22] M. Bertalmio, L. Vese, G. Sapiro, and S. Osher, “Simultaneous structure and texture image inpainting,” IEEE Trans. Image Processing, vol. 12, no. 8, pp. 882-889, Aug. 2003.
[23] R. Bornard, E. Lecan, L. Laborelli, and J. H. Chenot, “Missing data correction in still images and image sequences,” ACM Multimedia, Dec. 2002.
[24] I. Drori, D. Cohen-Or, H. Yeshurun, “Fragment-based image completion,” ACM Trans. Graphics, vol.22, no. 3, pp. 303-312, 2003.
[25] J. Jia, and C. K. Tang, “Inference of segmented color and texture description by tensor voting,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 26, no. 6, pp. 771-786, Jun. 2004.
[26] A. Criminisi, P. P’erez, and K. Toyama, “Region filling and object removal by examplar-based image inpainting,” IEEE Trans. Image Processing, vol. 13, no.9, pp. 1200-1212, Sep. 2004.
[27] J. F. Wang, H. J. Hsu, and S. C. Liao, “A novel framework for object removal from digital photogragh,” in Proc. IEEE Conf. Image Processing, Sep. 2005, vol. 2, pp. 73-76.
[28] H. J. Hsu, J. F. Wang, add S. C. Liao, “A Hybrid Algorithm With Artifact Detection Mechanism for Region Filling After Object Removal From a Digital Photograph,” IEEE Trans. on Image Processing, vol. 16, no. 6, pp. 1611-1622, Jun. 2007.
[29] J. F. Wang, H. J. Hsu, H. M. Wang, “Constrained Texture Synthesis by Sub-patch Texture Synthesis,” in Proc. IEEE Conf. Multimedia and Expo, Jun. 2004, pp. 635-638.
[30] S. Yang, Y. H. Hu, T. Q. Nguyen, and D. L. Tull, “Maximum-Likelihood Parameter Estimation for Image Rining-Aritifact Removal,” IEEE Tran. Circuits and Systems for Video Technology, vol. 11, no. 8, pp. 963-973, Aug. 2001.
[31] P. Tan, S. Lin, L. Quan, and H. Y. Shum, “Highlight Removal by Illumination-Constrained Inpainting,” in Proc. IEEE Conf. Computer Vision, Oct. 2003, vol. 1, pp. 164-169.
[32] G. A. Triantafyllidis, D. Tzovaras, and M. G. Strintzis, “Blocking Artifact Detection and Reduction in Compressed Data,” IEEE Tran. Circuits and Systems for Video Technology, vol. 12, no. 10, pp. 877-890, Oct. 2002.
[33] W. K. Pratt, Digital Image Processing. Reading, MA: Addison-Wesley, 2001.
[34] T. Gevers, "Image Segmentation and Similarity of Color-Texture Objects," IEEE Tran. Multimedia, vol.4, no. 4, pp. 509-516, Dec. 2000.
[35] P. Harrison, “A nonhierarchical procedure for re-synthesize of complex texture,” in Proc. Int. Conf. Central Europe Computer Graphics, Visualization, and Computer Vision, Feb. 2001.
[36] Massachusetts Inst. Technol. Media Lab. Vision Texture [Online]. Available: http://www-white.media.mit.edu/vismod/imagery/-VisionTexture/vistex.html
[37] A. Zalesny, V. Ferrari, G. Caenen, and L. van Gool., “Parallel composite texture synthesis, ” Texture workshop ECCV, Copenhagen, Denmark, Jun. 2002.
[38] H. J. Hsu, J. F. Wang, L. C. Yeh and Y. R. Chen, “Content-based Video Coding using Background Texture Analysis/Synthesis,” IEE Electronics Letter, 2007. (under review)
[39] A. Dumitra and B. G. Haskell, “A texture replacement method at the encoder for bit-rate reduction of compressed video,” IEEE Trans. Circuits Syst. Video Technol., vol. 13, no. 2, pp. 163-175, Feb. 2003.
[40] A. Dumitra and B. G. Haskell, “An Encoder-Decoder texture replacement method with application to content-based movie coding,” IEEE Trans. on Circuits Syst. Video Technol, vol. 14, no. 6, pp. 825-840, Jun. 2004.
[41] E.Z. Flores and J.C Rolon, “A method for bit-rate reduction of compressed video using texture analysis/synthesis,” in Proc.IEEE Workshop on SiPS, Nov. 2005, pp. 467-472.
[42] P. Ndjiki-Nya et al., “Improved H.264/AVC coding using texture analysis and synthesis,” in Proc. IEEE Conf. Image Processing, Sep. 2003, vol. 2, pp. 849-852.
[43] P. Ndjiki-Nya et al., ”A generic and automatic content-based approach for improved H.264/MPEG4-AVC video coding,” in Proc. IEEE Conf. Image Processing, Sep. 2005, pp. 874-877.
[44] P. Ndjiki-Nya et al., “A content-based video coding approach for rigid and non-rigid textures,” in Proc. IEEE Conf. Image Processing, Oct. 2006, pp. 3169-3172.
[45] P. Ndjiki-Nya et al., “Automatic detection of video synthesis related artifacts,” in Proc. IEEE Conf. Acoustics, Speech, and Signal Processing, May. 2004, pp. 733-736.
[46] Deng, Y.; Manjunath, B.S., “Unsupervised segmentation of color-texture regions in images and video” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, no. 8, pp. 800-810, 2001.
[47] P. Wu, B.S. Manjunath, S. Newsam and H.D. Shin, “A texture descriptor for browsing and similarity retrieval,” Signal Processing: Image Communication, vol. 16, pp. 33-43, 2000.
[48] J. F. Wang, H. J. Hsu, J. S. Lee, “Interactive Object Extraction/Removal System for Digital Camera,” in Proc. IEEE Conf. on Consumer Electronics, Jan. 2007.
[49] Z. Wang, F. Zhou, and F. Qi, “Inpainting thick image regions using isophote propagation,” in Proc. IEEE Conf. Image Processing, Oct. 2006, pp. 689-692.
[50] E. L. Pennec and S. Mallat, “Sparse geometric image representations with bandelets,” IEEE Trans. Image Processing, vol.14, no. 4, pp. 423-438, 2005.
[51] D. Tschumperle and R. Deriche, “Vector-valued image regularization with PDE's: A common framework for different applications,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 27, no. 4, pp. 506-517, 2005.
[52] L. Rudin, S. Osher, and E. Fatemi, “Nonlinear total variation based noise removal algorithms,” Phys. D, no. 60, pp. 259–268, 1992.
[53] L. Vese and S. Osher, “Modeling Textures with Total Variation Minimization and Oscillating Patterns in Image Processing,”, vol. 02-19, UCLA CAM Rep., May 2002.
校內：2009-01-10公開校外：2009-01-10公開