跳到主要內容

臺灣博碩士論文加值系統

(44.211.26.178) 您好!臺灣時間:2024/06/15 03:02
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:呂嘉祐
研究生(外文):LU, JIA-YOU
論文名稱:基於示例的適應性影像修補法
論文名稱(外文):An Adaptive Exemplar-Based Method for Image Inpainting
指導教授:藍呂興
指導教授(外文):LAN, LEU-SJING
口試委員:藍呂興郭柏佑莊賦祥
口試委員(外文):LAN, LEU-SJINGKUO, PO-YUJUANG, FUH-SHYANG
口試日期:2023-06-06
學位類別:碩士
校院名稱:國立雲林科技大學
系所名稱:電子工程系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2023
畢業學年度:111
語文別:中文
論文頁數:38
中文關鍵詞:影像修補基於示例適應性修補
外文關鍵詞:image inpaintingexemplar-basedadaptive inpainting
相關次數:
  • 被引用被引用:0
  • 點閱點閱:51
  • 評分評分:
  • 下載下載:7
  • 收藏至我的研究室書目清單書目收藏:0
影像修補是在影像內部有缺損的情況下,以人工合成的方式加以補入適當的影像內容,並要求填補影像與原影像自然接合,看不出人工修補的痕跡。本文針對基於示例的影像修補,在補塊填入時提出一種適應性修補的做法。此種方法不僅可避免使用最高匹配度單一補塊做修補所產生的填補邊界不連貫,也可降低選用多個候選補塊做均值融合導致的模糊,其原因在於我們利用了多個相似補塊間的綜合資訊做適應性的判斷處理。此外,在填充順序的決定上,我們引入結構張量的資訊,以更加適當地調整填補的優先順序,從而改進影像的修補結果。實驗結果顯示,使用適應性區塊填補,能確實改善非適應性區塊填補所帶來的影像模糊與影像邊緣不連貫現象。與其他既有做法比較,本文方法在真實影像的視覺與相關數據上,都呈現了具體的改善效果。
Image inpainting is an image processing technique to restore missing or damaged area in an image, requiring no visual artificial artifacts in between the in-painted part and the original image. This article presents an adaptive method for exemplar-based image inpainting. The proposed approach not only alleviates the mismatch effect brought about by using the single best matching patch, but also reduces the blurring phenomenon caused by using the fused patch. The adaptive scheme exploits the overall information of the candidate patches, and makes wise decisions to adaptively select a more appropriate patch to fit in the missing image blank. Besides, in choosing the order of fill-in boundary point, we incorporate the tensor information of each image pixel so that a better fill-in order can be determined. Extensive experiments demonstrate the improved performance of the proposed method, both visually and in numerical metric values.
摘要 i
ABSTRACT ii
誌謝 iii
目錄 iv
表目錄 vi
圖目錄 vii
第1章 緒論 1
1.1 前言 1
1.2 研究動機與目的 2
1.3 本文研究貢獻 2
1.4 全文架構 3
第2章 背景知識與相關研究 4
2.1 基於示例(Exemplar-Based)的影像修補 4
2.1.1 相似補塊匹配 6
2.2 相關研究 8
第3章 研究方法 9
3.1 研究流程簡介 9
3.2 適應性判斷修補 10
3.3 優先填充順序 12
第4章 實驗結果與分析 14
4.1 簡介 14
4.2 參數調整建議 14
4.3 實驗結果 15
4.3.1 適應性修補的結果比較 15
4.3.2 變換填充順序的結果比較 16
4.3.3 影像修補的結果比較 19
4.3.4 客觀比較指標 22
第5章 結論與後續研究 25
5.1 結論 25
5.2 後續研究 26
參考文獻 27


[1]M. Bertalmio, G. Sapiro and V. Caselles, "Image inpainting", Proc. 27th Annu. Conf. Comput. raph. Interact. Techn., pp. 417-424, Jul. 2000.
[2]N. Gopinath, K. Arjun, J. A. Shankar, and J. J. Nair, “Complex diffusion based image inpainting”, Proc. 2015 1st Int. Conf. Next Gener. Comput. Technol. NGCT 2015, no. September, pp. 976–980,2016.
[3]F. Wu, Y. Kong, W. Dong, and Y. Wu, “Gradient-aware blind face inpainting for deep face verification,” vol. 331, pp. 301–311, Feb. 2019.
[4]A. Colomer, V. Naranjo, K. Engan, and K. Skretting, “Assessment of sparse-based inpainting for retinal vessel removal,” Signal Process. Image Commun., vol. 59, pp. 73–82, Nov. 2017.
[5]U. Erkan and A. Kilicman, “Two new methods for removing salt-andpepper noise from digital images,” ScienceAsia, vol. 42, pp. 28–32, Feb. 2016.
[6]U. Erkan and L. Gökrem, “A new method based on pixel density in salt and pepper noise removal,” Turkish J. Electr. Eng. Comput. Sci., vol. 26, pp. 161–172, Jan. 2018.
[7]D. Tschumperlé and R. Deriche, “Vector-valued image regularization with PDEs: A common framework for different applications,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 27, no. 4, pp. 506–517, Apr. 2005.
[8]T. Chan and J. Shen, “Variational restoration of non-flat image features: Models and algorithms,” SIAM J. Appl. Math., vol. 61, no. 4, pp. 1338–1361, Jan. 2001.
[9]H. Grossauer, “A combined PDE and texture synthesis approach to inpainting,” in Proc. Eur. Conf. Comput. Vis., pp214-224, May. 2004.
[10]A. Criminisi, P. Pérez, and K. Toyama, “Region filling and object removal by examplar-based image inpainting,” IEEE Trans. Image Process., vol. 13, no. 9, pp. 1200–1212, Aug. 2004.
[11]A. Bugeau and M. Bertalmio, “Combining texture synthesis and diffusion for image inpainting,” in Proc. Int. Conf. Comput. Vis. Theory Appl., Jan. 2009, pp. 26–33.
[12]I. Drori, D. Cohen-Or, and H. Yeshurun, “Fragment-based image completion,” ACM Trans. Graph., vol. 22, no. 2003, pp. 303–312, Jul. 2003.
[13]D. Ding, S. Ram and J. J. Rodríguez, “Image inpainting using nonlocal texture matching and nonlinear filtering” , IEEE Trans. Image Process., vol. 28, no. 4, pp. 1705-1719, Apr. 2018.
[14]Z. Xu and J. Sun, “Image inpainting by patch propagation using patch sparsity,”IEEE Trans. Image Processing, vol. 19, no. 5, pp. 1153–1165, May 2010.
[15]S. Di Zenzo, “A note on the gradient of a multi-image,” Comput. Vision, Graphics,Image Process., vol. 33, no. 1, pp. 116–125, Jan. 1986.
[16]Le Meur O., J. Gautier, and C. Guillemot, “Examplar-based inpainting based on local geometry,” in Proc. 18th IEEE Int. Conf. Image Process., Sep. 2011, pp. 3401–3404.
[17]A. Wong and J. Orchard, “A nonlocal-means approach to exemplarbased inpainting,” in Proc. IEEE Int. Conf. Image Process., Oct. 2008, pp. 2600–2603.
[18]P. Arias, G. Facciolo, V. Caselles, and G. Sapiro, “A variational framework for exemplar-based image inpainting,” Int. J. Comput. Vis., vol. 93, no. 3, pp. 319–347, Jan. 2011.
[19]Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, “Image quality assessment: From error visibility to structural similarity,” IEEE Trans. Image Process., vol. 13, no. 4, pp. 600–612, Apr. 2004.
[20]J. Bednar and T. Watt, “Alpha-trimmed means and their relationship to median filters,” IEEE Trans. Acoust., Speech, Signal Process., vol. ASSP-32, no. 1, pp. 145–153, Feb. 1984.
[21]Berkeley dataset,
https://www2.eecs.berkeley.edu/Research/Projects/CS/vision/bsds/
[22]Le Meur, O., M. Ebdelli, and C. Guillemot. "Hierarchical Super-Resolution-Based-Inpainting." IEEE Transactions on Image Processing. vol. 22, no. 10, May. 2013, pp. 3779–3790
[23]T. Ogawa and M. Haseyama, “Image inpainting based on sparse representations with a perceptual metric,” EURASIP J. Adv. Signal Process., vol. 2013, no. 179, pp. 1–26, Dec. 2013.

QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top