Research on Images Identification Technology Based on Neural Network

Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 208)

Abstract

Image identification, with a mass of information computations, needs high speed and precision. The real-time and robustness of neural network accord the demands of the images identification. Aiming at the question that BP network easily to get bogged down in the partial dinky weakness, this paper proposed an improved neural network method, which can avoid the partial dinky and achieve the global minimum by adding the momentum factor in weight increment.

Keywords

Image identification Neural network BP algorithm 

References

  1. 1.
    Fei Y, Kunming W, Xin M, Shuangdong Z (2003) Application of BP neural network classifier for road traffic sign recognition. Comput Eng 10:73–77Google Scholar
  2. 2.
    Yao Z, Fei M, Li K (2007) Recognition of blue–green algae in lakes using distributive genetic algorithm-based neural networks. Neuro Comput 4:641–647Google Scholar
  3. 3.
    Peng S, Wang J (2005) Methods of image recognition based on neural networks. Electron Sci Technol 01:280–288Google Scholar
  4. 4.
    Hao-dong Z, Yong Z (2010) Image recognition model combining rough set with neural network. Comput Eng Appl 13:38–46Google Scholar
  5. 5.
    Cai-xia G, Jian-chang Y, Shou-feng J (2006) Recognition algorithm of the foreign fibers in cotton by BP neural networks. J Xi’an Univ Eng Sci Technol 20(5):542–544Google Scholar
  6. 6.
    Dan-qing W, Zhi-jun L (2005) Pattern recogition based on hopfield neural network. J Wuhan Yejin Univ Sci Technol 04:231–236 Google Scholar
  7. 7.
    Mingdong X, Li G, Guoxuan Z, Shijian L (2005) A new method of image recognition. Comput Eng 9:182–184Google Scholar
  8. 8.
    Ding-qiang Y, Shu-ping X, Jia-fu J (2008) Texture image recognition based on differentia evolution probabilistic neural network. Comput Eng Appl 11:289–295Google Scholar
  9. 9.
    Asvestas P, Matsopoulos FK, Nikita KS (2007) A power differentiation method of fractal dimension estimation for 2_D signals. J Vis Commun Image Represent 9:392–400CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London 2013

Authors and Affiliations

  1. 1.Educational Technology and Information CenterMudanjiang Medical UniversityMudanjiangChina

Personalised recommendations