Skip to main content
SpringerLink
Log in

A dyadic multi-resolution deep convolutional neural wavelet network for image classification

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

For almost the past four decades, image classification has gained a lot of attention in the field of pattern recognition due to its application in various fields. Given its importance, several approaches have been proposed up to now. In this paper, we will present a dyadic multi-resolution deep convolutional neural wavelets’ network approach for image classification. This approach consists of performing the classification of one class versus all the other classes of the dataset by the reconstruction of a Deep Convolutional Neural Wavelet Network (DCNWN). This network is based on the Neural Network (NN) architecture, the Fast Wavelet Transform (FWT) and the Adaboost algorithm. It consists, first, of extracting features using the FWT based on the Multi-Resolution Analysis (MRA). These features are used to calculate the inputs of the hidden layer. Second, those inputs are filtered by using the Adaboost algorithm to select the best ones corresponding to each image. Third, we create an AutoEncoder (AE) using wavelet networks of all images. Finally, we apply a pooling for each hidden layer of the wavelet network to obtain a DCNWN that permits the classification of one class and rejects all other classes of the dataset. Classification rates given by our approach show a clear improvement compared to those cited in this article.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

References

  1. Abdel-Hamid O, Mohamed A, Jiang H, Deng L, Penn G, Yu D (2014) Convolutional neural networks for speech recognition. IEEE/ACM Trans Audio, Speech, Lang Proc 22(10)

  2. Al-Jawfi R (2009) Handwriting arabic character recognition LeNet usingneural network. Int Arab J Info Technol (IAJIT) 6(3):304–311

    Google Scholar 

  3. Alonso D, Merjildo F, Ling L (2012) Enhancing the performance of Ada boost algorithms by introducing a frequency counting factor for weight distribution updating, progress in pattern recognition, image analysis, computer vision, and applications, lecture notes. Comput Sci 7441:527–553

    Google Scholar 

  4. Amar CB, Zaied M, Alimi AM (2005) Beta wavelets. Synthesis and application to lossy image compression. Adv Eng Softw 36:459–474

    Article  MATH  Google Scholar 

  5. Bengio Y (2009) Learning deep architectures for AI. Foundations and Trends® in. Mach Learn 2(1):1–127

    Article  MathSciNet  MATH  Google Scholar 

  6. Bonneau GP, Elber G, Hahmann S, Sauvage B (2008) Multiresolution Analysis. Chapt Math Visual J 83–114

  7. Chen Z, Wang J, He H, Huang X (2014) A fast deep learning system using gpu. IEEE Int Symposium Circ Syst 1552–1555

  8. Daugman J (2003) Demodulation by complex-valued wavelets forstochastic pattern recognition. Int’l J Wavel Multiresol Info Proc 1(1):1–17

    Article  MATH  Google Scholar 

  9. Deng L, Yu D (2014) Deep learning methods and applications. Found Trends® Sign Proc 7(3–4):197–387

    Article  MathSciNet  MATH  Google Scholar 

  10. ElAdel A, Ejbali R, Zaied M, Amar CB (2014) A new semantic approach for CBIR based on beta wavelet networkmodeling shape refined by texture and color features. Intell Data Eng Auto Learn 378–385

  11. ElAdel A, Ejbali R, Zaied M, Amar CB (2015) Dyadic multi-resolution analysis-based deep learning for Arabic handwritten character classification. Int Conf Tools Artific Intell 807–812

  12. ElAdel A, Ejbali R, Zaied M, Amar CB (2015) Deep learning with shallow architecture for image classification. Int Conf High Perform Comput Simulat 408–412

  13. Fei-Fei L, Fergus R, Perona P (2006) One-shot learning of object categories. IEEE Trans Pattern Anal Mach Intell 28(4):594–611

    Article  Google Scholar 

  14. Fei-Fei L, Perona P (2005) A bayesian hierarchical model for learning natural scene categories. Proc IEEE Conf Comput Vis Patt Recog 2:524–531

    Google Scholar 

  15. Griffin G, Holub A, Perona P. Caltech-256 object category dataset

  16. Hassairi S, Ejbali R, Zaied M (2015) Supervised image classification using deep convolutional wavelets network. Int Conf Tools Artific Intell 265–271

  17. Hassairi S, Ejbali R, Zaied M (2015) A deep convolutional neural wavelet network to supervised Arabic letter image classification. Int Conf Intell Syst Des Appl 207–212

  18. Hertel L, Barth E, Kaster T, Martinetz T (2015) Deep Convolutional Neural Networks as Generic Feature Extractors. 2015 International Joint Conference on Neural Networks (IJCNN), Killarney, pp 1–4

    Google Scholar 

  19. Hinton G (2006) A fast learning algorithm for deep belief nets. Neural Comput 18(7):1527–1554

    Article  MathSciNet  MATH  Google Scholar 

  20. Hinton G (2010) A practical guide to training restricted boltzmann machines. Momentum 9(1):926

    Google Scholar 

  21. Ikuro S, Nishimura NH, Kensuke Y (2015) APAC: augmented pattern classiffication with Neural Networks. J. CoRR. abs/1505.03229

  22. Iyengar S, Cho E, Phoha V (2002) Foundations of waveletnetworks and applications. Chapman Hall/CRC Press

  23. Jarrett K, Kavukcuoglu K, Ranzato M, LeCun Y (2009) Whatis the best multi-stage architecture for object recognition? ICCV 2146–2153

  24. Jawerth B, Sweldens W (1993) An overview of wavelet based multi resolution analyses. SIAM Rev J (SIAMRev) 36:377–412

    Article  MATH  Google Scholar 

  25. Jemai O, Zaied M, Amar CB, Alimi AM (2010) Fbwn:an architecture of fast beta wavelet networks for image classification. Int Joint Conf Neural Networks

  26. Jemai O, Zaied M, Ben Amar C, Alimi AM (2011) Fast Learning algorithmof wavelet network based on fast wavelet transform. Int J Patt Recog Artific Intell (IJPRAI) 25(8):1297–1319

    Article  MATH  Google Scholar 

  27. Kavukcuoglu K, Sermanet P, Boureau Y, Gregor K, Mathieu M, LeCun Y (2010) Learning Convolutional Feature Hierachies for Visual Recognition. 24th Annual Conference on Neural Information Processing Systems, Vancouver, pp 1090–1098

    Google Scholar 

  28. Khalifa M, BingRu Y (2011) A novel word based arabic handwritten recognition system using SVM classifier, advanced research on electronic commerce. Web Appl Commun 143:163–171

    Google Scholar 

  29. Krizhevsky A, Sutskever I, Hinton G (2012) Imagenet classification with deep convolutional neural networks. Neural Info Proc Syst 25

  30. Lazebnik S, Schmid C, Ponce J (2006) Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. Proc IEEE Conf Comput Vis Patt Recog 2:2169–2178

    Google Scholar 

  31. Le Q, Ngiam J, Coates A, Lahiri A, Prochnow B, Ng A (2011) On optimization methods for deep learning. 28th International Conference on Machine Learning, Washington DC, pp 265–272

    Google Scholar 

  32. LeCun Y (2012) Learning invariant feature hierarchies. Comput Vis - ECCV 496–505

  33. LeCun Y, Bengio Y (1995) Convolutional networks for images, speech, and time series. In: Arbib MA (ed) The Handbook of Brain Theory and Neural Networks. Massachusetts: MIT Press, Cambridge, pp 255–258

    Google Scholar 

  34. Liou C-Y, Cheng W-C, Liou J-W, Liou D-R (2014) Autoencoder for words. Neurocomputing 139:84–96

    Article  Google Scholar 

  35. Liu W, Ma T, Tao D, You J (2016) HSAE: a hessian regularized sparse auto-encoders. Neurocomputing 187:59–65

    Article  Google Scholar 

  36. Llzobi M, AL-amadi A, Dings L, Elmezain M (2013) A Hidden Markov Model-Based Approach with an Adaptive Threshold Model for Off-LineArabic Handwriting Recognition. The 12th International Conderence on Document Analysis and Recognition (ICDAR), Washington, DC, pp 945–949

    Google Scholar 

  37. Lzobi M, AL-amadi A, Al Aghbari Z, Dings L (2014) Gabor wavelet recognition approach for off-line handwritten arabic using explicitsegmentation. Image processing and communications challenges 5. Adv Intel Syst Comput J (AISC) 23:245–254

    Google Scholar 

  38. Martens J (2010) Deep learning with Hessian-free optimization. 27th International Conference on Machine Learning, Haifa, pp 735–742

    Google Scholar 

  39. Martens J, Sutskever I (2011) Learning recurrent neural networks with Hessian-free optimization. 28th International Conference on Machine Learning, Washington DC, pp 1033–1040

    Google Scholar 

  40. Nilsback M-E, Zisserman A (2006) A visual vocabulary for flower classification. Proc IEEE Conf Comput Vis Patt Recog 2:1447–1454

    Google Scholar 

  41. Oliva A, Torralba A (2001) Modeling the shape of the scene: a holistic representation of the spatial envelope. Int J Comput Vis 42(3):145–175

    Article  MATH  Google Scholar 

  42. Pati YC, Krishnaprasad PS (1993) Analysis and synthesis of feed forward neural networks using discrete affine wavelettransformations. IEEE Trans Neural Networks 4:73–85

    Article  Google Scholar 

  43. Penga X, Yana R, Zhaoa B, Tanga H, Yib Z (2014) Fast low rank representation based spatial pyramid matching for image classification. Comput Vis Patt Recog

  44. Pltz T, Fink GA (2009) Markov models for offline handwriting recognition: a survey. Int J Doc Anal Recog (IJDAR) 12(4):269–298

    Article  Google Scholar 

  45. Slimane F, Ingold R, Kanoun S, Alimi AM (2010) Impact of Character Models Choice on Arabic Text Recognition Performance. International Conference on Frontiers in Handwrinting Recognition, Kolkata, pp 670–675

    Google Scholar 

  46. Szu H, Telfer B, Kadambe S (1992) Neural network adaptativewavelets for signal representation and classification. Opt Eng 31:1907–1961

    Article  Google Scholar 

  47. Toth L (2014) Convolutional deep maxout networks for phone recognition. Proc Interspeech

  48. Wan L, Zeiler MD, Zhang S, LeCun Y, Fergus R (2013) Regularization of Neural Networks using DropConnect. 30th International Conference on Machine Learning, Atlanta Georgia, pp 1058–1066

    Google Scholar 

  49. Wang J, Yang J, Yu K, Lv F, Huang T, Gong Y (2010) Locality constrained linear coding for image classification. Proc IEEE Conf Comput Vis Patt Recog 3360–3367

  50. Weston J, Ratle F, Mobahi H, Collobert R (2012) Deep learning via semi-supervised embedding, neural networks: tricks of the trade. Lect Notes Comput Sci 7700:639–655

    Article  Google Scholar 

  51. Xu Q, Jiang S, Huang W, Duan L, Xu S (2013) Multi-feature fusion based spatial pyramid deep neural networks image classification. Comput Model New Technol 17(5C):207–212

    Google Scholar 

  52. Yang X, Liu W, Tao D, Cheng J (2017) Canonical correlation analysis networks for two-view image recognition’. Inf Sci 385–386:338–352

    Article  Google Scholar 

  53. Yang J, Yu K, Gong Y, Huang T (2009) Linear spatial pyramid matching using sparse coding for image classification. Proc IEEE Conf Comput Vis Patt Recog 1794–1801

  54. Zaied M, Said S, Jemai O, ben Amar C (2011) A novelapproach for face recognition based on fast learning algorithmand wavelet network theory. Int J Wavelets Multiresol Info Proc

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

    Article  Google Scholar 

  56. Zhou W (1999) Verification of the nonparametric characteristics of back propagation neural networks for image classification. IEEE Trans Geosci Remot Sens (TGARS) 37(2):771–779

    Article  MathSciNet  Google Scholar 

  57. Zou W, Yan WY, Shaker A (2011) Structure-Based Neural NetworkClassification for Panchromatic IKONOS Image using Wavelet-BasedFeatures. Eighth International Conference on Computer Graphics, Imagingand Visualization (CGIV), Singapore, pp 151–155

    Google Scholar 

  58. Zou WY, Zhu S, Ng AY, Yu K (2012) Deep learning of invariant features via simulated fixations in video. Adv Neu Info Proc Syst 3212–3220

Download references

Acknowledgements

The authors would like to acknowledge the financial support of this work by grants from General Direction of Scientific Research (DGRST), Tunisia, under the ARUB program.

Author information

Authors and Affiliations

  1. Research Laboratory in Intelligent Machines, University of Sfax, ENIS, BP 1173, Sfax, 3038, Tunisia

    Ridha Ejbali & Mourad Zaied

Authors
  1. Ridha Ejbali
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mourad Zaied
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ridha Ejbali.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ejbali, R., Zaied, M. A dyadic multi-resolution deep convolutional neural wavelet network for image classification. Multimed Tools Appl 77, 6149–6163 (2018). https://doi.org/10.1007/s11042-017-4523-2

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-017-4523-2

Keywords

Search

Navigation