Advertisement

Removal of Blocking Artifacts Using a Hierarchical Bayesian Approach

  • Rafael Molina
  • Aggelos K. Katsaggelos
  • Javier Mateos
Chapter

Abstract

Blocking artifacts are exhibited by block-compressed still images and sequences of images, primarily at high compression ratios. These artifacts are due to the independent processing (quantization) of the block transformed values of the intensity or the displaced frame difference. In this chapter, we provide a survey of the literature on the removal of such artifacts. We also apply the hierarchical Bayesian paradigm to the reconstruction of block discrete cosine transform compressed images and the estimation of the required hyperparameters. The evidence analysis within the hierarchical Bayesian paradigm is used to derive expressions for the iterative evaluation of these parameters. The proposed method allows for the combination of parameters estimated at the coder and decoder. The performance of the proposed algorithms is demonstrated experimentally.

Keywords

Discrete Cosine Transform Image Code Discrete Cosine Transform Coefficient Block Boundary Video Technology 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    G. Archer and D. M. Titterington. On some bayesian/regularization methods for image restoration. IEEE Trans. on Image Processing, 4: 989–995, 1995.CrossRefGoogle Scholar
  2. [2]
    A. Baskurt, R. Prost, and R. Goutte. Iterative constrained restoration of dctcompressed images. Signal Processing, 17: 201–211, 1989.MathSciNetCrossRefGoogle Scholar
  3. [3]
    J. O. Berger. Statistical Decision Theory and Bayesian Analysis. New York, Springer Verlag, 1985.MATHCrossRefGoogle Scholar
  4. [4]
    J. C. Brailean, T. Özcelik, and A. K. Katsaggelos. A video coding algorithm based on recovery techniques using mean field annealing. In Proceedings of the Visual Communication and Image Processing 95, SPIE Proc., pages 284–294, 1995.Google Scholar
  5. [5]
    W. L. Buntine. A Theory of Learning Classification Rules. PhD thesis, University of Technology, Sydney, Australia, 1991.Google Scholar
  6. [6]
    W. L. Buntine. Theory refinement on Bayesian networks. In Proc. of the Seventh Conference on Uncertainty in Artificial Intelligence, pages 52–60, 1991.Google Scholar
  7. [7]
    W. L. Buntine and A. Weigund. Bayesian back-propagation. Complex Systems, 5: 603–643, 1991.MATHGoogle Scholar
  8. [8]
    Y.-H. Chan and W.-C. Siu. An approach to subband DCT image coding. Journal of Visual Communication and Image Representation, 5 (1): 95–106, March 1994.MathSciNetCrossRefGoogle Scholar
  9. [9]
    S. S. O. Choy, Y.-H. Chan, and W.-C. Siu. Reduction of block-transform image coding artifacts by using local statistics of transform coefficients. IEEE Signal Processing Letters, 4 (1): 5–7, January 1997.CrossRefGoogle Scholar
  10. [10]
    G. F. Cooper and E. Herkovsits. A bayesian method for the induction of probabilistic networks from data. Machine Learning, 9: 309–347, 1992.MATHGoogle Scholar
  11. [11]
    M. Crouse and K Ramchandran. Nonlinear constrained least squares estimation to reduce artifacts in block transform-coded images. In Proceedings of the International Conference on Image Processing ICIP 95, volume 1, pages 462–465, 1995.Google Scholar
  12. [12]
    C. Derviaux, F. X. Coudoux, M. G. Gazalet, and P. Corlay. Blocking artifact reduction of DCT coded image sequences using a visually adaptive postprocessing. In Proceedings of the International Conference on Image Processing ICIP 96, volume 2, pages 5–8, 1996.Google Scholar
  13. [13]
    Y.-H. Fok, O. C. Au, and C. Chang. Bitrate and blocking artifact reduction by iterative pre-distorsion. In Proceedings of the International Conference on Image Processing ICIP 96, volume 2, pages 13–16, 1996.Google Scholar
  14. [14]
    S. F. Gull. Developments in maximum entropy data analysis. In J. Skilling, editor, Maximum Entropy and Bayesian Methods, pages 53–71. Kluwer, 1989.Google Scholar
  15. [15]
    Pong-Sik Ho and Min-Hwan Kim. Perceptually-adaptive image compression based on block dct. Journal of KISS[A] [Computer Systems and Theory], 22 (10): 1405–1415, 1995.Google Scholar
  16. [16]
    S. W. Hong, Y. H. Chan, and W. C. Siu. A practical real time postprocessing technique for block effect elimination. In Proceedings of the International Conference on Image Processing ICIP 96, volume 2, pages 21–24, 1996.Google Scholar
  17. [17]
    T.-C. Hsung, D. P.-K. Lun, and W.-C. Siu. A deblocking techniqhe for JPEG decoded image using wavelets transform modulus maxima representation. In Proceedings of the International Conference on Image Processing ICIP 96, volume 2, pages 561–564, 1996.Google Scholar
  18. [18]
    ISO/IEC). Digital Compression and Coding of Continuous-tone Still Images, Part 1, Requirements and Guidelines. ISO/IEC JTC 1/SC 29 International Standard 10918–1, 1994.Google Scholar
  19. [19]
    Y. Itoh. Detail preserving noise filtering for compressed image. IEICE Trans. on Communications, E79-B(10): 1459–1466, October 1996.Google Scholar
  20. [20]
    Y. Itoh. Detail-preserving noise filtering using binary index. In Proceedings of the Image and Video Processing IV Conf., SPIE Proc., volume 2666, pages 119–130, 1996.Google Scholar
  21. [21]
    B. Jeon, J. Jeong, and J. M. Jo. Blocking artifacts reduction in image coding based on minimum block boundary discontinuity. In Proceedings of the Visual Communications and Image Processing 95, pages 198–209, 1995.Google Scholar
  22. [22]
    J. Jeong and B. Jeon. Use of a class of two-dimensional functions for blocking artifacts reduction in image coding. In Proceedings of the International Conference on Image Processing ICIP 95, volume 1, pages 478–481, 1995.Google Scholar
  23. [23]
    H. Joung, U. Chong, and S. P. Kim. Block artifact reduction by optimization utilizing subband decomposition. In Proceedings of the 7th KSEA Northeast Regional Conference, 1996.Google Scholar
  24. [24]
    H. C. Kim and H. W. Park. Signal adaptive postprocessing for blocking effects reduction in JPEG image. In Proceedings of the International Conference on Image Processing ICIP 96, volume 2, pages 41–44, 1996.Google Scholar
  25. [25]
    C. Kuo and R. Hsieh. Adaptive postprocessor for block encoded images. IEEE Trans. on Circuits and Systems for Video Technology, 5 (4): 298–304, August 1995.CrossRefGoogle Scholar
  26. [26]
    K. Y. Kwak and R.A Haddad. Projection-based eigenvector decomposition for reduction of blocking artifacts of DCT coded image. In Proceedings of the International Conference on Image Processing ICIP 95, volume 2, pages 527530, 1995.Google Scholar
  27. [27]
    Y.-K. Lai, J. Li, and C.-C. J. Kuo. Image enhancement for low bit-rate jpeg and mpeg coding via postprocessing. In Proceedings of the Visual Communications and Image Processing ‘86, SPIE Proc., volume 2727, pages 1484–1494, 1996.Google Scholar
  28. [28]
    Y.-K. Lai, J. Li, and C.-C. J. Kuo. Removal of blocking artifacts of dct transform by classified space-frequency filtering. In Conference Record of The Twenty-Ninth Asilomar Conference on Signals, Systems and Computers, volume 2, pages 1457–1461, 1996.Google Scholar
  29. [29]
    I. Linares, R. Mersereau, and M. Smith. JPEG estimated spectrum adaptive post-filtering using image adaptive Q-tables and canny edge detectors. In Proceedings of the 1996 IEEE International Symposium on Circuits and Systems, volume 2, pages 722–725, 1996.Google Scholar
  30. [30]
    T.-S. Liu and N. Jayant. Adaptive posprocessing algorithms for low bit rate video signals. IEEE Trans. on Image Processing, 4 (7): 1032–1035, July 1995.CrossRefGoogle Scholar
  31. [31]
    J. Luo, C. W. Chen, K. J. Parker, and T. S. Huang. A new method for block effect removal in low bit-rate image compression. In Proceedings of the International Conference on Acoustics, Speech, and Signal Processing ICASSP 94, volume 5, pages 341–344, 1994.Google Scholar
  32. [32]
    J. Luo, C. W. Chen, K. J. Parker, and T. S. Huang. Artifact reduction in low bit rate DCT-based image compression. IEEE Trans. on Image Processing, 5 (9): 1363–1368, September 1996.CrossRefGoogle Scholar
  33. [33]
    W. E. Lynch, A. R. Reibman, and B. Liu. Post processing transform coded images using edges. In Proceedings of the 1995 International Conference on Acoustics, Speech, and Signal Processing, volume 4, 1995.Google Scholar
  34. [34]
    D. J. C. MacKay. Bayesian interpolation. Neural Computation, 4: 415–447, 1992.CrossRefGoogle Scholar
  35. [35]
    D. J. C. MacKay. A practical Bayesian framework for backprop networks. Neural Computation, 4: 448–472, 1992.CrossRefGoogle Scholar
  36. [36]
    D. J. C. MacKay. Hyperparameters: Optimize, or integrate out? Submitted to Neural Computation, 1995.Google Scholar
  37. [37]
    J. Mateos. Reconstrucción Automatica de imcígenes comprimidas mediante transformada coseno discreta usando métodos bayesianos. PhD thesis, E.T.S. Ing. Informatica. University of Granada, July 1998.Google Scholar
  38. [38]
    J. Mateos, C. Ilia, B. Jiménez, R. Molina, and A. K. Katsaggelos. Reduction of blocking artifacts in block transformed compressed color images. In Proceedings of the International Conference on Image Processing ICIP 98,1998. To be held.Google Scholar
  39. [39]
    J. Mateos, A. K. Katsaggelos, and R. Molina. Parameter estimation in regularized reconstruction of BDCT compressed images for reducing blocking artifacts. In Proceedings of the Conference on Digital Compression Technologies & Video Communications, SPIE Proc., volume 2952, pages 70–81, 1996.Google Scholar
  40. [40]
    J. Mateos, A. K. Katsaggelos, and R. Molina. A bayesian approach to estimate and transmit regularization parameters for reducing blocking artifacts. Submitted to IEEE Trans on Image Processing, 1998.Google Scholar
  41. [41]
    J. Mateos, R. Molina, and A. K. Katsaggelos. Estimating and transmitting regularization parameters for reducing blocking artifacts. In Proceedings of the 13th International Conference on Digital Signal Processing, pages 209–212, 1997.CrossRefGoogle Scholar
  42. [42]
    J. D. McDonnell, R. Shorten, and A. D. Fagan. An edge classification based approach to the post-processing of transform coded images. In Proceedings of the International Conference on Acoustics, Speech, and Signal Processing ICASSP 94, volume 5, pages 329–332, 1994.Google Scholar
  43. [43]
    S. Minami and A. Zakhor. An optimization approach for removing blocking effects in transform coding. IEEE Trans. on Circuits and Systems for Video Technology, 5 (2): 74–81, April 1995.CrossRefGoogle Scholar
  44. [44]
    R. Molina. On the hierarchical Bayesian approach to image restoration. application to astronomical images. IEEE Trans. on Pattern Analysis and Machine Intelligence, 16 (11): 1222–1228, 1994.CrossRefGoogle Scholar
  45. [45]
    R. Molina, A. K. Katsaggelos, and J. Mateos. Bayesian and regularization methods for hyperparameter estimation in image restoration. Submitted to IEEE Trans on Image Processing, 1997.Google Scholar
  46. [46]
    T. P. O’Rourke and R. L. Stevenson. Improved image decompression for reduced transform coding artifacts. In Proceedings of the Image and Video Processing II Conf., SPIE Proc., volume 2182, pages 90–101, 1994.Google Scholar
  47. [47]
    T. P. O’Rourke and R. L. Stevenson. Improved image decompression for reduced transform coding artifacts. IEEE Trans. on Circuits and Systems for Video Technology, 5 (6): 490–499, December 1995.CrossRefGoogle Scholar
  48. [48]
    T. Özcelik, J. C. Brailean, and A. K. Katsaggelos. Image and video compression algorithms based on recovery techniques using mean field annealing. Proceedings of the IEEE, 83 (2): 304–316, February 1995.CrossRefGoogle Scholar
  49. [49]
    H. Paek and S.-U. Lee. A projection-based post-processing technique to reducte blocking artifact using a prior information on DCT coefficients of adjacent blocks. In Proceedings of the International Conference on Image Processing ICIP 96, volume 2, pages 53–56, 1996.Google Scholar
  50. [50]
    Hoon Paek, Jong-Wook Park, and Sang-Uk Lee. Non-iterative post-processing technique for transform coded image sequence. In Proceedings of the International Conference on Image Processing ICIP 95, volume 3, pages 208–211, 1995.Google Scholar
  51. [51]
    W. B. Pennebaker and J. L. Mitchell. JPEG Still Image Compression Standard. Van Nostrand Reinhold, 1992.Google Scholar
  52. [52]
    H. A. Peterson, A.J. Ahumada, and A.B Watson. The visibility of DCT quantization noise. In Society for Information Display. Diggest of technical papers, pages 942–945, 1993.Google Scholar
  53. [53]
    H. A. Peterson, A.J. Ahumada, and A.B Watson. Visibility of dct quantization noise: spatial frequency summation. In Proceedings of the 1994 SID International Symposium Digest of Technical Papers, pages 704–7, 1994.Google Scholar
  54. [54]
    R. Prost, Y. Ding, and A. Baskurt. JPEG dequantization array for regularized decompression. IEEE Trans. on Image Processing, 6 (6): 883–888, June 1997.CrossRefGoogle Scholar
  55. [55]
    G. Ramamurthi and A. Gersho. Nonlinear space-variant postprocessing of block coded images. IEEE Trans. on Acoustic, Speech and Signal Processing, 34 (5): 1258–1269, October 1986.CrossRefGoogle Scholar
  56. [56]
    H. C. Reeves and J. S. Lim. Reduction of blocking effects in image coding. Optical Engineering, 23 (1): 34–37, January 1984.Google Scholar
  57. [57]
    S. J. Reeves and S. L. Eddins. Comments on “iterative procedures for reduction of blocking effects in transform image coding”. IEEE Trans. on Cirucits and Systems for Video Technology, 3 (6): 439–440, December 1993.CrossRefGoogle Scholar
  58. [58]
    D. G. Sampson, D. V. Papadimitriou, and G. Chamzas. Post-processing of block-coded images at low bitrates. In Proceedings of the International Conference on Image Processing ICIP 96, volume 2, pages 1–4, 1996.Google Scholar
  59. [59]
    K. Sauer. Enhancement of low bit-rate coded images using edge detection and estimation. CVGIP: Graphical Models and Image Processing, 53 (1): 52–62, January 1991.MATHCrossRefGoogle Scholar
  60. [60]
    D.A. Silverstein and S.A. Klein. Restoration of compressed images. In Proceedings of the Image and Video Compression Conf, SPIE Proc., volume 2186, pages 56–64, 1994.Google Scholar
  61. [61]
    D. J. Spiegelhalter and S.L. Lauritzen. Sequential updating of conditional probabilities on directed graphical structures. Networks, 20: 579–605, 1990.MathSciNetMATHCrossRefGoogle Scholar
  62. [62]
    R. L. Stevenson. Reduction of coding artifacts in transform image coding. In Proceedings of the International Conference on Acoustics, Speech, and Signal Processing ICASSP 93, volume 5, pages 401–404, 1993.Google Scholar
  63. [63]
    R. L. Stevenson. Reduction of coding artifacts in low-bit-rate video coding. In Proceedings of the 38th Midwest Symposium on Circuits and Systems., pages 854–857, August 1995.Google Scholar
  64. [64]
    C. E. M. Strauss, D. H. Wolpert, and D. R. Wolf. Alpha, evidence and the entropic prior. In A. Mohammed-Djafari, editor, Maximum Entropy and Bayesian Methods, Paris, pages 53–71. Kluwer, 1992.Google Scholar
  65. [65]
    A. Sultan and H.A. Latchman. Adaptive quantization scheme for mpeg video coders based on hvs (human visual system). In Proceedings of the Digital Video Compression: Algorithms and Technologies 1996, SPIE Proc., volume 2668, pages 181–188, 1996.Google Scholar
  66. [66]
    S. Suthaharan and H.R. Wu. Adaptive-neighbourhood image filtering for mpeg-1 coded images. In Proceedings of the Fourth International Symposium on Signal Processing and its Applications. ISSPA 96, volume 1, pages 166–167, 1996.Google Scholar
  67. [67]
    Soon Hie Tan, K. K. Pang, and K. N. Ngan. Classified perceptual coding with adaptive quantization. IEEE Trans. on Circuits and Systems for Video Technology, 6 (4): 375–388, August 1996.CrossRefGoogle Scholar
  68. [68]
    M. Temerinac and B. Edler. Overlapping block transform: Window design, fast algorithm, an image coding experiment. IEEE Trans. on Communications, 43 (9): 2417–2425, 1995.CrossRefGoogle Scholar
  69. [69]
    K.-H. Tzou. Post-filtering of transform-coded images. In Applications of the digital image processing XI, SPIE Proc., volume 974, pages 121–126, 1988.Google Scholar
  70. [70]
    J. L. Webb. Post-processing to reduce blocking artifacts for low bit-rate video coding using chrominance information. In Proceedings of the International Conference on Image Processing ICIP 96, volume 2, pages 9–12, 1996.Google Scholar
  71. [71]
    D. H. Wolpert. On the use of evidence in neural networks. In C. L. Giles, S. J. Hanson, and J. D. Cowan, editors, Advances in Neural Information Processing Systems 5, San Mateo, California, pages 539–546. Morgan Kaufmann, 1993.Google Scholar
  72. [72]
    Z. Xiong, M. T. Orchard, and Y.-Q. Zhang. A deblocking algorithm for JPEG compressed images using overcomplete wavelet representation. IEEE Trans. on Circuits and Systems for Video Technology, 7 (4): 433–437, April 1997.CrossRefGoogle Scholar
  73. [73]
    Li Yan. Adaptive spatial-temporal postprocessing for low bit-rate coded image sequence. In Proceedings of the image and video processing II conf, SPIE Proc., volume 2182, pages 102–109, 1994.Google Scholar
  74. [74]
    Li Yan. A nonlinear algorithm for enhancing low bit-rate coded motion video sequence. In Proceedings of the International Conference on Image Processing ICIP 94, volume 2, pages 923–927, 1994.Google Scholar
  75. [75]
    Y. Yang and N. P. Galatsanos. Edge-preserving reconstruction of compressed images using projections and a divide-and-conquer strategy. In Proceedings of the International Conference on Image Processing ICIP 94, volume 2, pages 535–539, November 1994.Google Scholar
  76. [76]
    Y. Yang and N. P. Galatsanos. Compression artifact removal using projections onto convex sets and line process modeling. IEEE Trans. on Image Processing, 6 (10): 1345–1357, October 1997.CrossRefGoogle Scholar
  77. [77]
    Y Yang, N. P. Galatsanos, and A. K. Katsaggelos. Regularized reconstruction to reduce blocking artifacts of block discrete cosine transform compressed images. IEEE Trans. on Circuits and Systems for Video Technology, 3 (6): 421–432, December 1993.CrossRefGoogle Scholar
  78. [78]
    Y. Yang, N. P. Galatsanos, and A. K. Katsaggelos. Projection-based spatially-adaptive reconstruction of block-transform compressed images. IEEE Trans. on Image Processing., 4 (7): 896–908, July 1995.CrossRefGoogle Scholar
  79. [79]
    A. Zakhor. Iterative procedures fror reduction of blocking effects in transform image coding. IEEE Trans. on Circuits and Systems for Video Technology, 2 (1): 91–95, March 1992.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media Dordrecht 1998

Authors and Affiliations

  • Rafael Molina
    • 1
  • Aggelos K. Katsaggelos
    • 2
  • Javier Mateos
    • 1
  1. 1.Departamento de Ciencias de la Computación e I.A.Universidad de GranadaGranadaSpain
  2. 2.Department of Electrical and Computer EngineeringNorthwestern UniversityEvanstonUSA

Personalised recommendations