DCT information recovery of erroneous image blocks by a neural predictor

In this paper, the problem of DCT information recovery in the transmission of coded visual data over packet networks is addressed. The loss of a packet conveying coded block data leads to the unsuccessful reconstruction of the relevant area, with consequent degradation of the received image quality. The proposed method allows recovery of a subset of the missing DCT coefficients sufficient to achieve good reconstruction quality of the lost block, based on the available surrounding information. To this purpose, a neural predictor was carefully designed and suitably trained with an appropriate set of synthetic and natural patterns. An extensive testing phase, performed on a large set of images with different frequency characteristics, revealed that the method provides very good reconstruction capabilities.

[1]  Huifang Sun,et al.  Concealment of damaged block transform coded images using projections onto convex sets , 1995, IEEE Trans. Image Process..

[2]  Yao Wang,et al.  Image reconstruction from partial subband images and its application in packet video transmission , 1991, Signal Process. Image Commun..

[3]  David G. Messerschmitt,et al.  Resynchronization of motion compensated video affected by ATM cell loss , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[4]  Thomas J. Ferguson,et al.  Self-synchronizing Huffman codes , 1984, IEEE Trans. Inf. Theory.

[5]  Yao Wang,et al.  Maximally smooth image recovery in transform coding , 1993, IEEE Trans. Commun..

[6]  Sang Uk Lee,et al.  On the error concealment technique for DCT based image coding , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

[7]  Bo Shen,et al.  Direct feature extraction from compressed images , 1996, Electronic Imaging.

[8]  Chung-Lin Huang,et al.  Hybrid cell loss concealment methods for MPEG-II-based packet video , 1997, Signal Process. Image Commun..

[9]  Ziad Al Kachouh,et al.  Exact DCT-based spatial domain interpolation of blocks in images , 1997, Proceedings of International Conference on Image Processing.

[10]  Luigi Atzori,et al.  Error concealment in video transmission over packet networks by a sketch-based approach , 1999, Signal Process. Image Commun..

[11]  Yao Wang,et al.  Error control and concealment for video communication: a review , 1998, Proc. IEEE.

[12]  A. R. Reibman,et al.  Self-synchronizing variable-length codes for image transmission , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[13]  A. S. Tom,et al.  Packet video for cell loss protection using deinterleaving and scrambling , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[14]  Robert M. Gray,et al.  Subband-coded image reconstruction for lossy packet networks , 1997, IEEE Trans. Image Process..

[15]  Andrzej Cichocki,et al.  Neural networks for optimization and signal processing , 1993 .

[16]  Mohammed Ghanbari,et al.  Two-layer coding of video signals for VBR networks , 1989, IEEE J. Sel. Areas Commun..

[17]  Farrokh Marvasti,et al.  Novel error concealment techniques for images in ATM environments , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).