An Underwater Laser Image Segmentation Algorithm Based on Pulse Coupled Neural Network and Morphology

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 215)

Abstract

Range-gated underwater laser imaging technology, which is very promising in oceanic research, deep sea exploration, and robotic works, is one of the most effective methods to suppress the effect of backward scattering of water medium. However, the special features of underwater laser images, such as speckle noise and nonuniform illumination, bring great difficulty for image segmentation. In this paper, an image segmentation algorithm which combines improved pulse coupled neural network with morphology is proposed. The morphology is applied to eliminate the speckle noise, while the cross-entropy is calculated as an optimization criterion for determination of the optimal segmentation. The experimental results of the proposed algorithm are compared with those of NCut, Mean-shift, Fuzzy C-means, and Watershed methods, and the quantitative evaluation confirms that the proposed algorithm is significantly superior to the other four algorithms in segmentation accuracy and robustness against speckle noise and nonuniform illumination.

Keywords

Underwater laser image Pulse coupled neural network Morphology Cross-entropy 

Notes

Acknowledgments

This work is supported by fundamental research funds for central universities (HEUCF110111), by National Natural Science Foundation of China (51009040\E091002), by National High-tech R&D Program of China (863 Program) (2011AA09A106), and by the China Postdoctoral Science Foundation (Award: 2012M510928).

References

  1. 1.
    Tulldahl HM, Anderson P, Olsson A (2006) Experimental evaluation of underwater range-gated viewing in natural waters. In: Electro-optical and infrared systems. Proceedings of SPIE, vol 6395, p 639506Google Scholar
  2. 2.
    Li H, Wang X, Bai T (2008) Nonuniformly illuminated image enhancement based on range-gated underwater imaging system. In: 2008 International conference on optical instruments and technology. Proceedings of SPIE, vol 7156, pp 71563EGoogle Scholar
  3. 3.
    Eckhorn R, Reitboeck HJ, Arndt M (1990) Feature linking via synchronization among distributed assemblies: simulation of results from cat cortex. Neural Comput 2(3):293–307CrossRefGoogle Scholar
  4. 4.
    Eckhorn R, Frien A, Bauer R (1993) High frequency oscillations in primary visual cortex of awake monkey. NeuroReport 4(3):243–246CrossRefGoogle Scholar
  5. 5.
    Wang ZB, Ma YD, Chen FY (2010) Review of pulse-coupled neural networks. Image Vision Comput 28(1):5–13CrossRefMATHMathSciNetGoogle Scholar
  6. 6.
    Rafael CG, Richard EW (2010) Digital Image Processing, 3rd edn. Publishing house of electronics industry, BeijingGoogle Scholar
  7. 7.
    Li CH, Lee CK (1993) Minimum cross entropy thresholding. Pattern Recogn 26(4):617–625Google Scholar
  8. 8.
    Xu SZ, Liu H, Song EM (2011) Marker-controlled watershed for lesion segmentation in mammograms. J Digit Imaging 24:754–763CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  1. 1.National Key Laboratory of Science and Technology on Underwater VehicleHarbin Engineering UniversityHarbinChina

Personalised recommendations