Rate-distortion optimized image compression based on image inpainting

详细信息    查看全文

• 作者：Wei Jiang
• 关键词：Image inpainting ; Rate ; distortion ; Image compression ; Perceptual quality
• 刊名：Multimedia Tools and Applications
• 出版年：2016
• 出版时间：January 2016
• 年：2016
• 卷：75
• 期：2
• 页码：919-933
• 全文大小：5,444 KB
• 参考文献：1.Bastani V, Helfroush MS, Kasiri K (2010) Image compression based on spatial redundancy removal and image inpainting. J Zhejiang Univ Sci C 11(2):92–100CrossRef
  2.Bertalmio M, Sapiro G, Caselles V, Ballester C (2000) Image inpainting. In Proc. ACM SIGGRAPH, pp. 417–424
  3.Bertalmio M, Vese L, Sapiro G, Osher S (2003) Simultaneous structure and texture image inpainting. IEEE Trans Image Process 12(8):882–889CrossRef
  4.Bertozzi, Esedoglu S, Gillette A (2007) Inpainting of binary images using the Cahn-Hilliard equation. IEEE Trans Image Process 16(1):285–291CrossRef MathSciNet MATH
  5.Bugeau, Bertalmio M, Caselles V, Sapiro G (2010) A comprehensive framework for image inpainting. IEEE Trans Image Process 19(10):2634–2645CrossRef MathSciNet
  6.Cai JF, Chan RH, Shen Z (2008) A framelet-based image inpainting algorithm. Appl Comput Harmon Anal 24(2):131–149CrossRef MathSciNet MATH
  7.Cai JF, Chan RH, Shen Z (2010) Simultaneous cartoon and texture inpainting. Inverse Probl Image 4(3):379–395CrossRef MathSciNet MATH
  8.Canny J (1986) A computational approach to edge detection. IEEE Trans Pattern Anal Mach Intell 8(6):679–698CrossRef
  9.Chan TF, Shen J, Zhou H-M (2006) Total variation wavelet inpainting. J Math Imaging Vision 25(1):107–125CrossRef MathSciNet
  10.Criminisi, Perez P, Toyama K (2004) Region filling and object removal by exemplar-based inpainting. IEEE Trans Image Process 13(9):1200–1212CrossRef
  11.Dobrosotskaya JA, Bertozzi AL (2008) A wavelet-laplace variational technique for image deconvolution and inpainting. IEEE Trans Image Process 17(5):657–663CrossRef MathSciNet
  12.Elad M, Starck JL, Querre P, Donoho DL (2005) Simultaneous cartoon and texture image inpainting using morphological component analysis (MCA). Appl Comput Harmon Anal 19(3):340–358CrossRef MathSciNet MATH
  13.Fadili MJ, Starck JL, Murtagh F (2009) Inpainting and zooming using sparse representations. Comput J 52(1):64–79CrossRef
  14.Grossauer H (2004) A combined PDE and texture synthesis approach to inpainting. In Proc. Eur. Conf. Comput. Vis. (ECCV’04), pp. 214–224
  15.Jiang W, Wang J, Yang J (2009) A novel algorithm of solving the optimal slope on rate-distortion curve for the given rate budget. J Donghua Univ 3:259–263
  16.Komodakis N, Tziritas G (2007) Image completion using efficient belief propagation via priority scheduling and dynamic pruning. IEEE Trans Image Process 16(11):2649–2661CrossRef MathSciNet
  17.Li YR, Shen Lx, Suter BW. Adaptive inpainting algorithm based on DCT induced wavelet regularization. IEEE Trans Image Process 22(2):752-763
  18.Li YR, Shen L, Suter BW (2013) Adaptive inpainting algorithm based on DCT induced wavelet regularization. IEEE Trans Image Process 22(2):752–763CrossRef MathSciNet
  19.Liu D, Sun X, Wu F, Li S, Zhang Y-Q (2007) Image compression with edge-based inpainting. IEEE Trans Circ Syst Video Technol 17(10):1273–1287CrossRef
  20.Liu D, Sun X, Wu F (2009) Edge-based inpainting and texture synthesis for image compression. Proc. Int. Conf. Multimedia & Expo pp. 1443–1447
  21.Masnou S (2002) Disocclusion: a variational approach using level lines. IEEE Trans Image Process 11(2):68–76CrossRef MathSciNet
  22.Ramchandran K, Vetterli M (1993) Best wavelet packet bases in a rate-distortion sense. IEEE Trans Image Process 2(2):160–175CrossRef
  23.Rane SD, Sapiro G, Bertalmio M (2003) Structure and texture filling-in of missing image blocks in wireless transmission and compression applications. IEEE Trans Image Process 12(3):296–303CrossRef MathSciNet
  24.Reid MM, Millar RJ, Black ND (1997) Second-generation image coding: an overview. ACM Comput Surv 29(1):3–29CrossRef
  25.Wang Z, Sheikh HR, Bovik AC (2002) No-reference perceptual quality assessment of JPEG compressed images. In Proc. IEEE Int. Conf. Image Processing (1):477–480
  26.Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13:600–612CrossRef
  27.Wang C, Sun X, Wu F, Xiong H (2006) Image compression with structure-aware inpainting. In Proc. IEEE Int. Symp. Circuits Syst. (ISCAS) pp. 1816–1819
  28.Wei Z, Ngan KN (2009) Spatio-temporal just noticeable distortion profile for grey scale image/video in DCT domain. IEEE Trans Circ Syst Video Technol 19(3):337–346CrossRef
  29.Wen YW, Chan RH, Yip AM (2012) A primal–dual method for total-variation-based wavelet domain inpainting. IEEE Trans Image Process 21(1):106–114CrossRef MathSciNet
  30.Wexler Y, Shechtman E, Irani M (2007) Space-time completion of video. IEEE Trans Pattern Anal Mach Intell 29(3):463–476CrossRef
  31.Wu Yd, Zhang Hy, Sun Y, Guo Hy (2009) Two image compression schemes based on image inpainting. CSO, Sanya, Hainan, China (1):816–820
  32.Xiong Z, Sun X, Wu F (2007) Image coding with parameter-assistant inpainting. Proc Int Conf Image Process 2:369–372
  33.Xiong Z, Sun X, Wu F (2010) Block-based image compression with parameter-assistant inpainting. IEEE Trans Image Process 19(6):1651–1657CrossRef MathSciNet
  
• 作者单位：Wei Jiang (1) (2)
  
  1. School of Computer and Information Engineering, Shanghai University of Electric Power, Shanghai, 200090, China
  2. 702, No.35, Gaoqing road 2878, Shanghai, 200123, China
  
• 刊物类别：Computer Science
• 刊物主题：Multimedia Information Systems
  Computer Communication Networks
  Data Structures, Cryptology and Information Theory
  Special Purpose and Application-Based Systems
  
• 出版者：Springer Netherlands
• ISSN：1573-7721

文摘

Inspired by recent advancements in image inpainting techniques, an image coding framework is proposed in this paper. In the framework, an original image is analyzed at the encoder side such that a number of the regions are skipped intentionally. A drop map is extracted and compressed into the generated bit stream to indicate the skipped regions. The image is recovered through the inpainting process by taking advantage of the available portion of the decoded image and the drop map at the decoder. Furthermore, the rate-distortion optimization is introduced to select the blocks to be removed for the better performance. Only the blocks containing certain visual features and satisfying rate-distortion criterion are dropped. A practical system is constructed to verify the effectiveness of the compression approach. Evaluations have been made in comparison with baseline JPEG and H.264/AVC. Compared to the baseline JPEG, the proposed algorithm obtains obvious visual quality improvements, as well as PSNR gains. Moreover, the proposed algorithm outperforms H.264/AVC intra coding under the low bit rates. Keywords Image inpainting Rate-distortion Image compression Perceptual quality