Advertisement

Unsupervised Segmentation of Satellite Images Based on Neural Network and Genetic Algorithm

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 309)

Abstract

Segmentation is one of the important processes in image analysis to extract the necessary but hidden information in the image. The success of the image analysis is based on the outcome of the segmentation process. There are number of methods proposed for the segmentation of satellite images. Soft computing approaches such as fuzzy logic, neural networks, and genetic algorithm are most widely used for the segmentation of satellite images. But, every method has its own advantages and disadvantages. In this paper, a new approach based on the combination of genetic algorithm and feed forward neural network is proposed for the segmentation of satellite images. In this process, the genetic algorithm selects and feeds the fittest individual to the neural network. This feed forward network performs the segmentation. The computational cost is drastically reduced due to this cooperative and parallel approach. Experimental result illustrates the efficiency of the proposed approach.

Keywords

Segmentation Clustering Image enhancement Genetic algorithm Neural network 

References

  1. 1.
    Ganesan, P., Rajini, V.: A method to segment color images based on modified fuzzy-possibilistic-c-means clustering algorithm. In: Recent Advances in Space Technology Services and Climate Change (RSTSCC), 2010. IEEE (2010)Google Scholar
  2. 2.
    Gonzalez, R.C.: Digital Image Processing, 2nd edn. Prentice Hall of India (2006)Google Scholar
  3. 3.
    Awad, M., Chehdi, K., Nasri, A.: Multi-component image segmentation using a hybrid dynamic genetic algorithm and fuzzy C-means. IET Image Process. 3(2), 52–62 (2009)Google Scholar
  4. 4.
    Awad, M., Chehdi, K., Nasri, A.: Multi-component image segmentation using genetic algorithm and artificial neural network. IEEE Geosci. Remote Sens. Lett. 4(4), 571–575 (2007)CrossRefGoogle Scholar
  5. 5.
    Goldberg, D.E.: Genetic Algorithms in Search. Optimization and Machine Learning. Addison-Wesley, New York (1989)MATHGoogle Scholar
  6. 6.
    Bhanu, S. Lee, S., Ming, J.: Adaptive image segmentation using a genetic algorithm. IEEE Trans. Syst. Man Cybern. 1543–1567 (1995)Google Scholar
  7. 7.
    Zhang, H.Z., Xiang, C.B., Song, J.Z.: Application of Improved Adaptive Genetic Algorithm to Image Segmentation in Real-time. Optics and Precision Engineering, pp. 333–336 (2008)Google Scholar
  8. 8.
    Farmer, M.E., Shugars, D.: Application of genetic algorithms for wrapper-based image segmentation and classification. In: IEEE Congress on Evolutionary Computation, pp. 1300–1307 (2006)Google Scholar
  9. 9.
    Feitosa, R.Q., Costa, G.A.O.P., Cazes, T.B.: A genetic approach for the automatic adaptation of segmentation parameters. In: OBIA06 (2006)Google Scholar
  10. 10.
    Aria, E., Saradjian, M., Amini, J., Lucas, C.: Generalized occurrence matrix to classify IRS-1D images using neural network. In: Proceedings of XXth ISPRS Congress, Turkey, pp. 117–123 (2004)Google Scholar

Copyright information

© Springer India 2015

Authors and Affiliations

  • P. Ganesan
    • 1
  • V. Rajini
    • 2
  • B.S. Sathish
    • 1
  • V. Kalist
    • 1
  1. 1.Department of Electronics and Control EngineeringSathyabama UniversityChennaiIndia
  2. 2.Department of Electrical and Electronics EngineeringSSN College of EngineeringChennaiIndia

Personalised recommendations