成功大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	王泓銘 Wang, Hong-Ming
論文名稱：	影像處理之物體移除演算法及硬體架構 Object Removal Algorithm/Hardware in Image Processing
指導教授：	王駿發 Wang, Jhing-Fa
學位類別：	碩士 Master
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：	2004
畢業學年度：	92
語文別：	英文
論文頁數：	68
中文關鍵詞：	影像處理、物體移除
外文關鍵詞：	object removal, image processing
相關次數：	點閱：99 下載：4
分享至:	分享至facebook 分享至twitter

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

　　我們提供一個影像處理領域中新的物體移除演算法。此演算法可以在數位圖片中濾除及補償我們不想要的物體。對於不同紋理背景，我們整合加權內插法和子區塊紋理合成來填補濾除的區域。子區塊紋理合成可以一次貼一條目標，而加權內插法可使用區塊平滑法。此演算法基於規則性則有利整合於數位像機上。在這篇論文，我們也比較之前別人的演算法。我們也提出第一個紋理合成順序於限制的紋理合成。此演算法有比較快的計算能力及其規則性適合於積體電路設計，可以達到比較高的效能。

　　We propose a novel algorithm for object removal in image processing. The proposed algorithm can filter and compensate the unwanted object in digital photograph. For different background texture, we present an object removal algorithm integrates weighted interpolation and sub-patch texture synthesis to fill the lost region. The sub-patch texture synthesis algorithm can past a line each time and weighted interpolation technique with　block-smoothing method. The proposed regular algorithms are suitable to be integrated in smart digital camera due to the regularity. The comparison of previous algorithms is also provided in this thesis. We present a first algorithm used in constrained texture synthesis by regular synthesizing order. The proposed algorithm can achieve better performance, faster computation and regular architecture for VLSI design.

摘要............................................................................i
Abstract.......................................................................ii
誌謝..........................................................................iii
Contents.......................................................................iv
List of Tables.................................................................vi
List of Figures...............................................................vii
Chapter 1 Introduction..........................................................1
1 Object Removal Algorithms...................................................1
2 Motivations.................................................................2
3 Thesis Organization.........................................................2
Chapter 2 Previous Works........................................................3
1 Texture Synthesis...........................................................3
1.1 Pixel-based Texture Synthesis.............................................3
1.1.1 Single-resolution Algorithm.............................................4
1.1.2 Multi-resolution Algorithm..............................................8
1.1.3 Constrained Texture Synthesis..........................................10
1.2 Patch-based Texture Synthesis............................................13
2 Image Inpainting...........................................................15
3 Integration of Texture Synthesis and Image Inpainting......................19
4 General system flow for object removal algorithm...........................22
Chapter 3 Proposed Object Removal Algorithms...................................23
1 System Flow................................................................23
2 Pre-processing – Boundary Extension.......................................24
3 Proposed Sub-patch Texture Synthesis.......................................25
3.1 Sub-patch Texture Synthesis..............................................25
3.1.1 Parameter Definition...................................................25
3.1.2 Scalable Searching Neighborhood........................................28
3.1.3 Synthesizing Order.....................................................28
3.2 Adaptive Size of Sub-patch Neighborhood..................................29
4 Proposed Weighted Interpolation............................................29
4.1 Interpolation Background.................................................29
4.2 Gaussian Pyramid Background..............................................31
4.2 Weighted Interpolation...................................................34
5 Post-Processing – Block Smoothing.........................................36
Chapter 4 Experimental Results.................................................37
1 Experimental Results for Vistex Texture....................................37
2 Experimental Results for Ordinary Image....................................38
2.1 Human Removal by Weighted Interpolation Method...........................39
2.2 Object Removal by Sub-patch Synthesis Algorithm..........................43
2.3 Object Removal Using Integration of Sub-patch Synthesis and Weighted
      Interpolation............................................................46
Chapter 5 VLSI Design for Real-time System.....................................47
1 System Overview of Our Algorithm...........................................47
2 Proposed Architecture for Searching Block..................................48
2.1 Pipelined Architecture...................................................48
2.2 The Improved Pipelining Searching Architecture...........................50
Chapter 6 Conclusion and Future Work...........................................52
References.....................................................................54
                                    

[1] L. Y. Wei and M. Levoy, “Fast texture synthesis using tree-structured vector quantization”, Proceedings of SIGGRAPH, pp. 479-488, July, 2000.
[2] A. A. Efros and W. T. Freeman, “Image quilting for texture synthesis and transfer”, Proceedings of SIGGRAPH, pp. 341-346, 2001.
[3] L. Liang, C. Liu, Y. Q. Xu, B. Guo, and H. Y. Shum, “Real-time texture synthesis by patch-based sampling”, ACM Transaction on graphics, vol. 20, pp. 127-150, 2001.
[4] Y. H. Hu and R. A. Sambhare, “Constrained texture synthesis for image post processing”, IEEE International Conference on Multimedia and Expo, vol. 1, no. 6-9, pp. 113-116, July, 2003.
[5] E. Simoncelli, and J. Portilla, “Texture characterization via joint statistics of wavelet coefficient magnitudes”, International Conference on image processing, vol. 1, pp. 62-66, October, 1998.
[6] S. D. Rane, G. Sapiro, and M. Bertalmio, “Structure and texture filling-in of missing image blocks in wireless transmission and compression applications”, IEEE Transactions on image processing, vol. 12, no. 3, March, 2003.
[7] M. Bertalmio, L. Vese, G. Sapiro, and S. Osher, “Simultaneous structure and texture image inpainting”, IEEE Transactions on image processing, vol. 12, no. 8, August, 2003.
[8] A. Criminisi, P. P’erez and K. Toyama, “Object removal by exemplar-based inpainting”, IEEE Conference on Computer Vision and pattern recognition, 2003.
[9] Iddo Drori, Daniel Cohen-Or, Hezy Yeshurun, “fragment-based image completion”, ACM Transactions on Graphics, vol.22, no. 3, July, 2003.
[10]MIT Media Lab. Vision texture. http://www-white.media.mit.edu/vismod/imagery/-VisionTexture/vistex.html
[11] M. Ashikhmin, “Synthesizing natural textures”, ACM symposium on interactive 3D graphics, 217-226, 2001.
[12] Jhing-Fa Wang, Han-Jen Hsu, and Hong-Ming Wang, “Constrained Texture Synthesis by Scalable Sub-patch Algorithm,” IEEE Conference on Multimedia and Expo, June, 2004.

校內：立即公開
校外：2004-08-16公開

簡易檢索 / 詳目顯示

相關論文