Analysis of Pattern Storage Network with Simulated Annealing for Storage and Recalling of Compressed Image Using SOM

  • Manu Pratap Singh
  • Rinku Sharma Dixit
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 236)


In this paper, we are analyzing the SOM-HNN for storage and recalling of fingerprint images. The feature extraction of these images is performed with FFT, DWT, and SOM. These feature vectors are stored as associative memory in Hopfield Neural Network with Hebbian learning and Pseudoinverse learning rules. The objective of this study is to determine the optimal weight matrix for efficient recalling of the memorized pattern for the presented noisy or distorted and incomplete prototype patterns from the Hopfield network using Simulated Annealing. This process minimizes the effect of false minima in the recalling process.


Pattern storage network SOM FFT DWT Simulated annealing 


  1. 1.
    Davey, N., Hunt, S.P., Adams, R.: High capacity recurrent associative memories. Neurocomputing - IJON 62, 459–491 (2008). doi: 10.1016/j.neucom.2004.02.007 CrossRefGoogle Scholar
  2. 2.
    Gill, S., Sharma, N.K., Singh, M.P.: Study of pattern storage techniques in self organizing map using hopfield energy function analysis. In: Proceedings of ADCOM–2006, pp. 640–641. (1–4244-0716-8/06/2006/IEEE). Google Scholar
  3. 3.
    Stroeve, S., Kappen, B., Gielen, S.: Stimulus segmentation in a stochastic neural network with exogenous signals. In: Ninth International Conference on Artificial Neural Networks, 1999, ICANN 99, vol. 2, pp. 732–737 (1999)Google Scholar
  4. 4.
    Sandirasegaram, N., English, R.: Comparative analysis of feature extraction (2D FFT & wavelet) and classification (Lp metric distances, MLP NN & HNet) algorithms for SAR imagery. In. Proceedings Of SPIE 5808, 314–325 (2005)CrossRefGoogle Scholar
  5. 5.
    Kaski, S., Kangas, J., Kohonen, T.: Bibliography of self-organizing map (SOM) papers: 1981–1997. Neural Comput. Surv. 1(3 &4), 1–176 (1998)Google Scholar
  6. 6.
    Kohonen, T.: Self-organized formation of topologically correct feature maps. Biol. Cybernet. 43, 59–69 (1982b)CrossRefzbMATHMathSciNetGoogle Scholar
  7. 7.
    Kohonen, T.: Self-organizing formation of topologically correct feature maps. Biol. Cybern. 43, 59–69 (1982)Google Scholar
  8. 8.
    Hubel, D.H., Wiesel, T.N.: Receptive fields, binocular interaction, and functional architecture in the cat’s visual cortex. J. Physiol. London 160, 106–154 (1962)Google Scholar
  9. 9.
    Colin, M., Utku, S., Hugues, B.: Introduction of a Hebbian unsupervised learning algorithm to boost the encoding capacity of Hopfield networks, neural networks. In: Proceedings of the IEEE International Joint Conference on IJCNN ’05. 2005, vol. 3, pp. 1552–1557 (2005)Google Scholar
  10. 10.
    Gorodnichy, D.O.: The influence of self connection on the performance of pseudoinverse autoassociative networks. In: Proceedings of CVPR Workshop on Face Processing in Vodeo (FPIV ’04) (2004)Google Scholar
  11. 11.
    Emmert-Streib, F.: Active learning in recurrent neural networks facilitated by a hebb-like learning rule with memory. Neural Inf. Process. Lett. Rev. 9(2), 31–40 (2005)Google Scholar
  12. 12.
    Labiouse, C.L., Salah, A.A., Starikova, I.: The impact of connectivity on the memory capacity and the retrieval dynamics of hopfield-type networks. In: Proceedings of the Santa Fe Complex Systems Summer School, pp. 77–84 (2002)Google Scholar
  13. 13.
    Davey, N., Adams, R.G.: Stochastic dynamics and high capacity associative memories. In: Proceedings of the Ninth International Conference on Neural Information Processing, pp. 1666–1671 (2002)Google Scholar
  14. 14.
    Jeffrey, W., Rosner, R.: Optimization algorithms: simulated annealing and neural network processing. Astrophys. J. 310(1), 473–481 (1986)CrossRefGoogle Scholar
  15. 15.
    Salcedo Sanz, S.: A hybrid hopfield network-simulated annealing approach for frequency assignment in satellite communication systems. IEEE Trans. Syst. Man Cybern. B: Cybern. 34(2), 1108–1116 (2004)Google Scholar

Copyright information

© Springer India 2014

Authors and Affiliations

  1. 1.Department of Computer ScienceInstitute of Engineering and Technology, Dr. B.R.Ambedkar UniversityAgra (Khandari)India
  2. 2.Manav Rachna College of Engineering, Sector-43Aravali Hills, Surajkund—Badkal RoadFaridabadIndia

Personalised recommendations