淡江大學覺生紀念圖書館 (TKU Library)
進階搜尋


下載電子全文限經由淡江IP使用) 
系統識別號 U0002-2309201409500300
中文論文名稱 累進式全景圖影像修補
英文論文名稱 Progressive Panoramic Image Completion
校院名稱 淡江大學
系所名稱(中) 資訊工程學系碩士班
系所名稱(英) Department of Computer Science and Information Engineering
學年度 102
學期 2
出版年 103
研究生中文姓名 葉昊禹
研究生英文姓名 Hao-Yu Yeh
學號 601411191
學位類別 碩士
語文別 中文
第二語文別 英文
口試日期 2014-07-24
論文頁數 47頁
口試委員 指導教授-顏淑惠
委員-陳朝欽
委員-林慧珍
委員-顏淑惠
中文關鍵字 影像修補  馬可夫隨機場  優先權式可靠度傳遞  信賴度值 
英文關鍵字 Image Completion  Markov Random Field  Priority Belief Propagation  confidence value 
學科別分類 學科別應用科學資訊工程
中文摘要 本論文提出一基於優先權式信賴度傳遞的方法能夠修補缺失區域位在影像四周的情況。要能夠達到這個目的,本方法重新定義馬可夫隨機場中節點的產生方式,並且使用漸進式方法一層一層的去修補影像。同時為了降低其運算量,我們先限制取得候選區塊的範圍之後再使用亮度和飽和度來對馬可夫隨機場中之每個節點的候選區塊做篩選。最後為了產生一張視覺上美觀的結果圖,因此在修補的階段我們加入了節點的目標區塊和候選區塊間之相似度與信賴度值這兩個條件來判斷每個節點是否可以修補。
實驗結果顯示,不只缺失區域位在影像四周的修補結果,同時缺失區域位在影像中間的情況其修補的結果都令人滿意。
英文摘要 In this paper we propose a priority belief propagation based method to complete the missing region located on the periphery of the input image. To reach this goal, we redefine the nodes of Markov Random Field (MRF) and use onion-based approach to complete the image. Meanwhile, avoiding the heavy computation, we restrict the range to getting candidates for MRF. Then, applying intensity and saturation as criteria to filter the candidate of each node of MRF. Finally, we combine the similarity between MRF node’s target and best candidate patch and confidence value to decide whether the node is suitable to complete or not. From the experiments shows that our method successfully produces the visual plausible results.
論文目次 目錄
第一章 緒論 1
第二章 相關文獻回顧 4
第三章 研究方法 10
3.1 priority BP與馬可夫隨機場(Markov Random Field) 13
3.2 Modified priority BP 20
3.2-1:定義MRF節點和取得候選區塊 20
3.2-2:計算基礎門檻值 22
3.2-3:候選區塊分群 23
3.2-4:Modified Priority BP 24
3.2-5:填補缺失區域的方法 27
第四章 實驗結果與討論 29
第五章 結論與未來研究方向 35
參考文獻 37
附錄:英文論文 39

圖目錄
圖 1 拼接產生的全景圖[8] 2
圖 2 為填補完成的全景圖(示意圖) [8] 2
圖 3 N. Komodakis et al. [10]的實驗結果 6
圖 4 對缺失區域在四周的影像使用priority BP的結果[11] 7
圖 5 J. Kopf et al. [11]的實驗結果 8
圖 6 K. He et al. [8]的流程示意圖 9
圖 7 系統流程圖 11
圖 8 待修補影像[11] 12
圖 9 遮罩影像(黑色代表缺失區域,白色代表已知) 12
圖 10 MRF的基本架構[10] 13
圖 11 Vp和Vpq的示意圖[10] 15
圖 12 節點接收和傳遞訊息的示意圖[10] 15
圖 13 priority BP演算法[10] 19
圖 14 圖中紅點為初始MRF節點 21
圖 15 圖中黃點為運作priority BP的節點 21
圖 16 圖中白點皆代表候選區塊左上角的座標 22
圖 17 target patch's intensity channel的示意圖(空白表示缺失點) 25
圖 18 target patch填入極值的示意圖 25
圖 19 填補缺失區域示意圖 28
圖 20 實驗結果1 31
圖 21 實驗結果2 32
圖 22 實驗結果3 33
圖 23 實驗結果4 33
圖 24 Initial patch size的影響 34
圖 25 confidence map的影響 34
參考文獻 [1] P. Arias, G. Facciolo, V. Caselles and G. Sapiro, "A Variational Framework for Exemplar-Based Image Inpainting," International Journal of Computer Vision, pp. 319-347, July 2011.
[2] M. Bertalmio, G. Sapiro, V. Caselles and C. Ballester, "Image inpainting," Proceedings of the 27th Annual Conference on Computer Graphics and Interactive Techniques, pp. 417-424, 25-27 July 2000.
[3] J. Choi and C. Hahm, “An Exemplar-Based Image Inpainting Method with Search Region Prior,” IEEE 2nd Global Conference on Consumer Electronics, pp. 68-71, 1-4 October 2013.
[4] S. C. Chung, T. W. Kuan, C. P. Lu and H. Y. Lin, "A New Approach of Image Inpainting Based on PSO Algorithm," IEEE International Conference on Orange Technologies, pp. 205-209, 12-16 March 2013.
[5] A. Criminisi, P. Perez and K. Toyama, "Region Filling and Object Removal by Exemplar-Based Image Inpainting," IEEE Transactions on Image Processing, pp. 1200-1212, September 2004.
[6] E. Hassan, H. Abbas and H. Mohamed, “Image Inpainting Based on Image Segmentation and Segment Classification,” IEEE International Conference on Control System, Computing and Engineering, pp. 28-33, November 2013.
[7] J. Hays and A. A. Efros, "Scene Completion Using Millions of Photographs," ACM Transaction on Graphics, Vol.26, No.3, Article 4,, July 2007.
[8] K. He, H. Chang and J. Sun, "Rectangling Panoramic Images via Warping," ACM Transactions on Graphics, Vol. 32, No. 4, Article 79, July 2013.
[9] K. He and J. Sun, “Statistics of Patch Offsets for Image Completion,” Proceedings of the 12th European Conference on Computer Vision, pp. 16-29, 7-13 October 2012.
[10] N. Komodakis and G. Tziritas, "Image Completion Using Efficient Belief Propagation via Priority Scheduling and Dynamic Pruning," IEEE Transactions on Image Processing, Vols. VOL. 16,, no. NO. 11, pp. 2649-2661, November 2007.
[11] J. Kopf, W. Kienzle, S. Drucker and S. B. Kang, "Quality Prediction for Image Completion," ACM Transactions on Graphics, Vol. 31, No. 6, Article 131, November 2012.
[12] J. Lee, D. Lee and R. Park, “Robust Exemplar-Based Inpainting Algorithm Using Region Segmentation,” IEEE Transactions on Consumer Electronics, pp. 553-561, May 2012.
[13] C. Liu, Y. Guo, L. Pan, Q. Peng and F. Zhang, “Image Completion Based on Views of Large Displacement,” The Visual Computer, pp. 833-841, September 2007.
[14] Y. Liu and V. Caselles, "Exemplar-Based Image Inpainting Using Multiscale Graph Cuts," IEEE Transactions on Image Processing, pp. 1699-1711, May 2013.
[15] R. Martinez-Noriega, A. Roumy and G. Blanchard, "Exemplar-Based Image Inpainting: Fast Priority and Coherent Nearest Neighbor Search," IEEE International Workshop on Machine Learning for Signal Processing, pp. 1-6, 23-26 September 2012.
[16] R. Martinez-Noriega and A. Roumy, "Prior and Macro-Filling Order For Image Completion," IEEE International Conference on Image Processing, pp. 719-723, 15-18 September 2013.
[17] Y. Pritch, E. Kav-Venaki and S. Peleg, “Shift-Map Image Editing,” IEEE 12th International Conference on Computer Vision, pp. 151-158, September 2009.
[18] Z. Xie, F. Zhang and C. Zhang, "An Adaptive Matching Algorithm for Image Inpainting," IEEE International Conference on Electronics, Communications and Control, pp. 1293-1296, 9-11 September 2011.
[19] M. Zhang, L. Zhang, Y. Sun, L. Feng and W. Ma, "Auto cropping for digital photographs," IEEE International Conference on Multimedia and Expo, 6-8 July 2005.
論文使用權限
  • 同意紙本無償授權給館內讀者為學術之目的重製使用,於2014-09-24公開。
  • 同意授權瀏覽/列印電子全文服務,於2014-09-24起公開。


  • 若您有任何疑問,請與我們聯絡!
    圖書館: 請來電 (02)2621-5656 轉 2281 或 來信