Skip to main content
SpringerLink
Log in

A review of wave-net identical learning & filling-in in a decomposition space of (JPG-JPEG) sampled images

  • Published:
Artificial Intelligence Review Aims and scope Submit manuscript

Abstract

Continuous flow to send images via encrypted wireless channels may reduce the efficiency of transmission. This is due to the damage or loss of the numerous macro-blocks from these images. Therefore, it is difficult to rebuild these patches from the point of reception. Many algorithms have been proposed in the past decade, particularly error concealment (EC) algorithms. In this paper, we focus on the algorithms that have high efficiency to fill-in the corrupted patches. On the other hand, we also present a new way of detecting the horizontal and vertical gradients especially, in the un-smooth patches. This improves the edge detector filter. Ultimately, a novel scheme for vertical and horizontal interpolation between the corrupted pixels and the non-corrupted adjacent pixels is achieved by improving the efficiency of filling-in. We used a new technique known as the wave-net model. This model combines the wavelet with the neural network classifier (NNC). The neural network was trained in advance to reduce the error extent for the pixels that may occur in the error. The experimental results were convincing and close to the desired. The proposed method is able to enhance image quality in term of both visual perception and the blurriness effects (BE).

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Arafiotis D, Bull DR, Canagarajah N (2006) Spatial error concealment with edge related perceptual consideration. J Signal Process Image Commun 21(2): 130–142

    Google Scholar 

  • Atzori L, De Natalef Francesco GB (1999) Concealment in video transmission over packet networks by a sketch-based approach. J Signal Process Image Commun 15(1–2): 57–76

    Google Scholar 

  • Ballester C, Bertalmio M, Caselles V, Sapiro G, Verdera J (2001) Filling-in by joint interpolation of vector fields and gray levels. IEEE Trans Image Process 10(8): 1200–1211

    MATH  MathSciNet  Google Scholar 

  • Bellil W, Ben C, Alimi AM (2006) Synthesis of wavelet filters using wavelet neural networks. Trans Eng Comput Technol 13: 108–111

    Google Scholar 

  • Bergman R, Nachlieli H, Ruckenstein G (2007) Detection of textured areas in images using a disorganization indicator based on component counts, HP Laboratories Israel HPL-2005-175(R.1)

  • Bertalmio M, Sapiro G, Caselles V, Ballester C (2000) Image inpainting. Int Conf Comput Graph Interact Tech (ICCGIT ‘00), pp 417–424

  • Bertalmio M, Vese L, Sapiro G, Osher S (2003a) Simultaneous structure and texture image inpainting. IEEE Trans Image Process 12(8)

  • Bertalmio M, Vese L, Sapiro G, Osher S (2003b) Image filling-in in a decomposition space. IEEE Int Conf Image Process (ICIP ‘03)

  • Canny J (1986) A computational approach to edge detection. IEEE Trans Pattern Anal Mach Intell 8(6): 679–698

    Google Scholar 

  • Chang EY (1998) An image coding and reconstruction scheme for mobile computing. The 5th international workshop on interactive distributed multimedia systems and telecommunication services(IWIDMSTS ‘98), vol 1483, pp 137–148

  • Chen Y, Hu Y, Au OC, Li H, Chen CW (2008) Video error concealment using spatial-temporal boundary matching and partial differential equation. IEEE Trans Multimed 10(1): 2–15

    Google Scholar 

  • Christopoulos C, Skodras A, Ebrahimi T (2000) The JPEG:2000 still image coding system: an overview. IEEE Trans Consum Electron 46(4): 1103–1127

    Google Scholar 

  • Cohen A, Daubechies I, Feauveau J-C (1992) Bases of compactly supported wavelets. Commun Pure Appl Math 45(5): 485–560

    MATH  MathSciNet  Google Scholar 

  • Criminisi A, Perez P, Toyama K (2004) Region filling and object removal by exemplar-based image inpainting. IEEE Trans Image Process 13(9): 1200–1212

    Google Scholar 

  • Cybenko G (1989) Approximation by superpositions of a sigmoidal function. Math Control Signals Syst 2: 303–314

    MATH  MathSciNet  Google Scholar 

  • Daubechies I (1992) Ten lectures on wavelets. J Appl Math 61: 357

    MathSciNet  Google Scholar 

  • Daugman JG (1988) Complete discrete 2-D Gabor transforms by neural networks for image analysis and compression. IEEE Trans Acoust Speech Signal Process 36(7): 1169–1179

    MATH  Google Scholar 

  • Devabhaktuni VK et al (1999) Robust training of microwave neural models. IEEE MTT-S international microwave symposium digest, Anaheim, CA, pp 145–148

  • Donoho D, Johnstone IM, Kerkyacharian G, Picard D (1995) Wavelet shrinkage: asymptotia with discussion. J R Stat Soc Ser B 57: 301–369

    MATH  MathSciNet  Google Scholar 

  • Du TDH (2006) Using structure and texture filling-in of missing H.264 image blocks in fading channel transmission. In: IPCV conference, pp 121–130

  • Dubeau F, Elmejdani S, Ksantini R (2004) Non-uniform haar wavelets. J Appl Math Comput 159(3): 675–693

    MATH  MathSciNet  Google Scholar 

  • Edgar SG-T, Vicente A-A, Jose FR-C (2006) Improving wavelet-networks performance with a new correlation-based initialization method and training algorithm. IEEE Int Conf Comput (CIC ‘06), pp 11–17

  • Efros AA, Leung TK (1999) Texture synthesis by nonparametric sampling. IEEE Int Conf Comput Vis 2: 133–1038

    Google Scholar 

  • Felix A, Yoav B (1996) Adaptive thresholding of wavelet coefficients. J Comput Stat Data Anal 22: 351–361

    Google Scholar 

  • Franti P, Nevalainen O, Kaukoranta T (1994) Compression of digital images by blocks truncation coding : a survey. Comput J 37(4): 308–332

    Google Scholar 

  • Gasquet C, Witomski P (2000) Analyse de Fourier et Applications, p 368

  • Ghanbari M, Sferidis V (1993) Cell-loss concealment of ATM networks. IEEE Trans Circuits Syst Video Technol 3: 238–247

    Google Scholar 

  • Haralick RM (1984) Digital step edges from zero crossing of second directional derivatives. IEEE Trans Pattern Anal Mach Intell 6(1): 58–68

    Google Scholar 

  • Harrison P (2001) A non-hierarchical procedure for re-synthesis of complex texture (In WSCG ‘01), pp 190–197

  • Heller PN (1995) Rank ‘M’ wavelets with ‘N’ vanishing moments. SIAM J Matrix Anal Appl 16(2): 502–519

    MATH  MathSciNet  Google Scholar 

  • Hemami SS (1995) Digital image coding for robust multimedia transmission. J Multimed Commun Video Coding

  • Hirani A, Totsuka T (1996) Combining frequency and spatial domain information for fast interactive image noise removal. IEEE Int Conf Comput Graph Interact Tech (ICCCITNR ‘96) pp 269–276

  • Hornik K, Stinchcombe M, White H (1989) Multi-layer feed-forward networks are universal approximators. Neural networks 2: 359–366

    Google Scholar 

  • Hornik K, Stinchcombe M, White H, Auer P (1994) Degree of approximation results for feed-forward networks approximating unknown mappings and their derivatives. J Neural Comput 6(6): 1262–1275

    MATH  Google Scholar 

  • Hsia S-C (2004) An edge-oriented spatial interpolation for consecutive block error concealment. IEEE Signal Process Lett 11(6): 577–580

    MathSciNet  Google Scholar 

  • Jawerth B, Sweldens W (1994) Overview of wavelet based multi-resolution analysis. SIAM Rev 36(3): 377–412

    MATH  MathSciNet  Google Scholar 

  • Jia J, Tang C-K (2003) Image repairing: robust image synthesis by adaptive ND tensor voting. IEEE Comput Soc Conf Comput Vis Pattern Recognit 1: 643

    Google Scholar 

  • Karu K, Jain AK, Bolle RM (1996) Is there any texture in the image? J Pattern Recogn 29(9): 1437–1446

    Google Scholar 

  • Khelila K, Bekkab REH, Djebaria A, Rouvaenc JM (2007) Multiple description wavelet-based image coding using correlating transforms. AEU-Int J Electron Commun 61: 411–417

    Google Scholar 

  • Kokaram AC, Morris RD, Fitzgerald WJ, Rayner PJW (1995) Detection of missing data in image sequences. IEEE Trans Image Process 4(11): 1496–1508

    Google Scholar 

  • Krzyzak A, Linder T (1998) Radial basis function networks and complexity regularization in function learning. IEEE Trans Neural Netw 9: 247–256

    Google Scholar 

  • Kwok TY, Yeung DY (1997) Constructive algorithms for structure learning in feed-forward neural networks for regression problems. IEEE Trans Neural Netw 8: 630–645

    Google Scholar 

  • Lyengar SS, Cho EC, Phoha VV (2002) Foundations of wavelet networks and applications. Book on Neural Networks Software, p 258

  • Mallat SG (1989) A theory for multi-resolution signal decomposition: the wavelet transform. IEEE Trans Pattern Anal Mach Intell 11(7): 674–693

    MATH  Google Scholar 

  • Mallat S (2000) Une exploration des signaux en Ondelettes, les éditions de l’école polytechnique

  • Mallat SG (2008) A wavelet tour of signal processing. Book on Signal Processing, Wavelet 700

  • Nievergelt Y (1999) Wavelets made easy, Birkhauser, Boston. Journal Test of Significance Based on Wavelet Thresholding and Neyman’s, p 297

  • Pancha P, El Zarki M (1994) MPEG coding for variable bit-rate video transmission. IEEE Mag Commun 32(5): 54–66

    Google Scholar 

  • Park JW, Lee SU (1999) of corrupted image data based on the NURBS interpolation. IEEE Trans Circuits Syst Video Technol 9: 1003–1008

    Google Scholar 

  • Pati YC, Krishnaprasad PS (1990) Discrete affine wavelet transforms for analysis and synthesis of feed-forward neural networks. IEEE Int Conf Adv Neural Inf Process Syst 3: 743–749

    Google Scholar 

  • Pati YC, Krishnaprasad PS (1993) Analysis and synthesis of feed-forward neural networks using discrete affine wavelet transformations. IEEE Trans Neural Netw 4(1): 73–85

    Google Scholar 

  • Rane SD, Remus J, Sapiro G (2002) Wavelet-domain reconstruction of lost blocks in wireless image transmission and packet-switched network. IEEE Int Conf Image Process 1: 309–312

    Google Scholar 

  • 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): 296–303

    MathSciNet  Google Scholar 

  • Reed R (1993) Pruning algorithms: a survey. IEEE Trans Neural Netw 4: 740–747

    Google Scholar 

  • Rioul O, Vetterli M (1991) Wavelets and signal processing. IEEE Mag Signal Process 8(4): 14–38

    Google Scholar 

  • Rogers JK, Cosman PC (1998) Wavelet zerotree image compression with packetization. IEEE Lett Signal Process 5(5): 105–107

    Google Scholar 

  • Salama P, Shroff NB, Coyle EJ, Delp EJ (1995) Error concealment techniques for encoded video streams. IEEE Int Conf Image Process (ICIP ‘95) 1: 9–12

    Google Scholar 

  • Sapiro SG, Bertalmio M (2002) Wavelet domain-reconstruction of lost blocks in wireless image transmission and packet-switched networks. Department of Electrical and Computer Engineering, MN, 55455, USA, pp 1–4

  • Scareseli F, Tsoi AC (1998) Universal approximation using feed-forward neural network: a survey of some existing methods, and some new results. Neural Netw 11: 15–37

    Google Scholar 

  • Servetto SD, Ramchandran K, Orchard MT (1999) Image coding based on a morphological representation of wavelet data. IEEE Trans Image Process 8(9): 1161–1174

    Google Scholar 

  • Shneier MO (1982) Extracting linear features from images using pyramids. IEEE Trans Syst Man Cybern 12: 569–572

    Google Scholar 

  • Simoncelli EP, Portilla J (1998) Texture characterization via joint statistics wavelet coefficient magnitudes. Int Conf on Image Proc 1: 62–66

    Google Scholar 

  • Skodras AN, Christopoulos CA, Ebrahimi T (2001) 2000: the upcoming still image compression standard. Pattern Recognit Lett 22(12): 1337–1345

    MATH  Google Scholar 

  • Smith M, Barnwell T (1986) Exact reconstruction techniques for tree-structured sub-band coders. IEEE Trans Acoust Speech Signal Process 34(3): 434–441

    Google Scholar 

  • Song L, Ma X, Songyu Y (2007) Adaptive pixel interpolation for spatial error concealment. J Signal Process Syst, pp 710–715

  • Steffen P, Heller P, Gopinath RA, Burrus CS (1993) Theory of regular M-band wavelet bases. IEEE Trans Signal Process 41: 3497–3511

    MATH  Google Scholar 

  • Suh J-W, Ho Y-S (1997) Error concealment based on directional interpolation. IEEE Trans Consum Electron 43(3): 295–302

    Google Scholar 

  • Sun H, Kwok W (1995) Concealment of damaged block transform coded images. IEEE Trans Image Process 4(4): 470–477

    Google Scholar 

  • Sun Q, Bi N, Huang D (2001) A introduction to multi-band wavelets. Zhejiang University Press, Zhejiang

    Google Scholar 

  • Szu HH, Telfer BA, Kadambe SL (1992) Neural network adaptive wavelets for signal representation and classification. J Opt Eng 31(9): 1907–1916

    Google Scholar 

  • Tamura S, Tateishi M (1997) Capabilities of a four-layered feed-forward neural network: four layer versus three. IEEE Trans Neural Netw 8: 251–255

    Google Scholar 

  • Thuillard M (2002) A review of wavelet networks, wave-nets, fuzzy wave-nets, and their applications. J Intell Technol Ser, pp 43–60

  • Tian J, Wells RO (1998) A fast implementation of wavelet transform for M-band filter banks. IEEE Int Conf 3391: 534–545

    Google Scholar 

  • Tom AS, Yeh CL, Chu F (1991) Packet video for cell loss protection using deinterleaving and scrambling. IEEE Int Conf Acoust Speech Signal Process (ICCSSP ‘91) 4: 2857–2860

    Google Scholar 

  • Ulichney R (1994) Digital halftoning. Seminar lecture notes-society for information display, vol 1, pp 1–10

  • Vese LA, Osher SJ (2003) Modeling textures with total variation minimization and oscillating patterns in image processing. J Sci Comput Math Stat 19(1–3): 553–572

    MATH  MathSciNet  Google Scholar 

  • Villiers J, Barnard E (1992) Back-propagation neural networks with one and two hidden layers. IEEE Trans Neural Netw 4: 136–141

    Google Scholar 

  • Wada M (1989) Selective recovery of video packet loss using error concealment. IEEE J Sel Areas Commun 7(5): 807–814

    Google Scholar 

  • Wang Y, Zhu Q-F, Shaw L (1993) Maximally smooth image recovery in transform coding. IEEE Trans Commun 41(10): 1544–1551

    MATH  Google Scholar 

  • Wexler Y, Shechtman E, Irani M (2004) IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol 1, pp 120–127

  • Yates F (1993) The analysis of replicated experiments when the field results are incomplete. Emp J Exp 129–142

  • Ye X, Loh NK (1993) Dynamic system identification using recurrent radial basis function network. Proc Am Control Conf 3: 2912–2916

    Google Scholar 

  • Zalesny A, Ferrari V, Caenen G, Gool LV (2002) Parallel composite texture synthesis. In: Texture 2002 workshop in conjunction with ECCV 2002, pp 151–155

  • Zhang Q, Benveniste A (1992) Wavelet networks. IEEE Trans Neural Netw 3(6): 889–898

    Google Scholar 

  • Zhu Q, Wang Y, Shaw L (1993) Coding and cell loss recovery in det based packet video. IEEE Trans Circuits Syst Video Technol 3: 248–258

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer & Communication Engineering, Faculty of Engineering, University of Putra Malaysia, 43300, Serdang, Selangor, Malaysia

    Alaa Khamees Al-Azzawi

  2. Department of Computer & Communication Engineering, Faculty of Engineering, University of Putra Malaysia, 43400 UPM, Serdang, Selangor, Malaysia

    M. Iqbal Saripan & Adznan Jantan

  3. Department of Multimedia, Faculty of Science and Computer Technology, University Putra Malaysia, 43400 UPM, Serdang, Selangor, Malaysia

    Rahmita Wirza O. K. Rahmat

Authors
  1. Alaa Khamees Al-Azzawi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. M. Iqbal Saripan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Adznan Jantan
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Rahmita Wirza O. K. Rahmat
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Alaa Khamees Al-Azzawi.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Al-Azzawi, A.K., Saripan, M.I., Jantan, A. et al. A review of wave-net identical learning & filling-in in a decomposition space of (JPG-JPEG) sampled images. Artif Intell Rev 34, 309–342 (2010). https://doi.org/10.1007/s10462-010-9177-7

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10462-010-9177-7

Keywords

Search

Navigation