Advertisement

Morph-CNN: A Morphological Convolutional Neural Network for Image Classification

  • Dorra Mellouli
  • Tarek M. Hamdani
  • Mounir Ben Ayed
  • Adel M. Alimi
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10635)

Abstract

Deep neural networks, an emergent type of feed forward networks, have gained a lot of interest especially for computer vision problems such as analyzing and understanding digital images. In this paper, a new deep learning architecture is proposed for image analysis and recognition. Two key ingredients are involved in our architecture. First, we used the convolutional neural network, as it is well adapted for image processing since it is the most used form of stored documents. Second, a morphological feature extraction is integrated mainly thanks to its positive impact on enhancing image quality. We have validated our Morph-CNN on multi digits recognition. A study of the impact of morphological operators on the performance measure was conducted.

Keywords

Deep learning Convolutional neural network Morphological operators Morphological convolutional neural network Image classification 

References

  1. 1.
    LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)CrossRefGoogle Scholar
  2. 2.
    Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Netw. 61, 85–117 (2015)CrossRefGoogle Scholar
  3. 3.
    LeCun, Y., Bengio, Y.: Convolutional networks for images, speech, and time series. The Handbook of Brain Theory and Neural Networks, vol. 3361, 10 (1995)Google Scholar
  4. 4.
    Serra, J.: Image Analysis and Mathematical Morphology, vol. 1. Academic Press (1982)Google Scholar
  5. 5.
    Scherer, D., Müller, A., Behnke, S.: Evaluation of pooling operations in convolutional architectures for object recognition. In: Diamantaras, K., Duch, W., Iliadis, L.S. (eds.) ICANN 2010. LNCS, vol. 6354, pp. 92–101. Springer, Heidelberg (2010). doi: 10.1007/978-3-642-15825-4_10 CrossRefGoogle Scholar
  6. 6.
    Masci, J., Angulo, J., Schmidhuber, J.: A learning framework for morphological operators using counter–harmonic mean. In: Hendriks, C.L.L., Borgefors, G., Strand, R. (eds.) ISMM 2013. LNCS, vol. 7883, pp. 329–340. Springer, Heidelberg (2013). doi: 10.1007/978-3-642-38294-9_28 CrossRefGoogle Scholar
  7. 7.
    Bullen, P.S.: Handbook of Means and Their Inequalities, vol. 560. Springer, Netherlands (2013)zbMATHGoogle Scholar
  8. 8.
    Angulo, J.: Pseudo-morphological image diffusion using the counter-harmonic paradigm. In: Blanc-Talon, J., Bone, D., Philips, W., Popescu, D., Scheunders, P. (eds.) ACIVS 2010. LNCS, vol. 6474, pp. 426–437. Springer, Heidelberg (2010). doi: 10.1007/978-3-642-17688-3_40 CrossRefGoogle Scholar
  9. 9.
    Netzer, Y., et al.: Reading digits in natural images with unsupervised feature learning. In: NIPS Workshop on Deep Learning and Unsupervised Feature Learning, vol. 2 (2011)Google Scholar
  10. 10.
    Goodfellow, I.J., et al.: Multi-digit number recognition from street view imagery using deep convolutional neural networks. arXiv preprint arXiv:1312.6082 (2013)
  11. 11.
    LeCun, Y., Cortes, C., Burges, C.J.C.: MNIST handwritten digit database. AT&T Labs, 2 (2010), http://yann.lecun.com/exdb/mnist
  12. 12.
    Lin, M., Chen, Q., Yan, S.: Network in network. arXiv preprint arXiv:1312.4400 (2013)
  13. 13.
    Zeiler, M.D., Fergus, R.: Stochastic pooling for regularization of deep convolutional neural networks. arXiv preprint arXiv:1301.3557 (2013)
  14. 14.
    Goodfellow, I.J., et al.: Maxout networks. arXiv preprint arXiv:1302.4389 (2013)
  15. 15.
    Liang, M., Hu, X.: Recurrent convolutional neural network for object recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)Google Scholar
  16. 16.
    Moussa, S.B., et al.: New features using fractal multi-dimensions for generalized Arabic font recognition. Pattern Recognit. Lett. 31(5), 361–371 (2010)CrossRefGoogle Scholar
  17. 17.
    Bezine, H., Alimi, A.M., Derbel, N.: Handwriting trajectory movements controlled by a beta-elliptic model. TC 1 (2003)Google Scholar
  18. 18.
    Alimi, A.M.: Evolutionary computation for the recognition of on-line cursive handwriting. IETE J. Res. 48(5), 385–396 (2002)CrossRefGoogle Scholar
  19. 19.
    Boubaker, H., Kherallah, M., Alimi, A.M.: New algorithm of straight or curved baseline detection for short arabic handwritten writing. In: 10th International Conference on Document Analysis and Recognition, ICDAR 2009. IEEE (2009)Google Scholar
  20. 20.
    Slimane, F., et al.: A study on font-family and font-size recognition applied to Arabic word images at ultra-low resolution. Pattern Recognit. Lett. 34(2), 209–218 (2013)CrossRefMathSciNetGoogle Scholar
  21. 21.
    Elbaati, A., et al.: Arabic handwriting recognition using restored stroke chronology. In: 10th International Conference on Document Analysis and Recognition, ICDAR 2009. IEEE (2009)Google Scholar
  22. 22.
    Baccour, L., Alimi, A.M., John, R.I.: Similarity measures for intuitionistic fuzzy sets: state of the art. J. Intell. Fuzzy Syst. 24(1), 37–49 (2013)zbMATHMathSciNetGoogle Scholar
  23. 23.
    Dhahri, H., Alimi, A.M.: The modified differential evolution and the RBF (MDE-RBF) neural network for time series prediction. In: International Joint Conference on Neural Networks, IJCNN 2006. IEEE (2006)Google Scholar
  24. 24.
    Bouaziz, S., Dhahri, H., Alimi, A.M., Abraham, A.: A hybrid learning algorithm for evolving flexible beta basis function neural tree model. Neurocomputing 117, 107–117 (2013)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Dorra Mellouli
    • 1
  • Tarek M. Hamdani
    • 1
  • Mounir Ben Ayed
    • 1
  • Adel M. Alimi
    • 1
  1. 1.REGIM-Lab: REsearch Groups in Intelligent MachinesUniversity of Sfax, National Engineering School of Sfax (ENIS)SfaxTunisia

Personalised recommendations