J4 ›› 2010, Vol. 45 ›› Issue (7): 86-93.

• Articles • Previous Articles     Next Articles

Multi-region image segmentation based on pulse coupled neural network

XU Guang-zhu1, LIU Ming2, REN Dong1, MA Yi-de3, LIU Xiao-li1   

  1. 1. Institute of Intelligent Vision and Image Information, College of Computer and Information Technology,
    China Three Gorges University, Yichang 443002, Hubei, China;
    2. Experiments Center of Art Academy, China Three Gorges University, Yichang 443002, Hubei, China;
    3. School of Information Science & Engineering, Lanzhou University, Lanzhou 730000, Gansu, China
  • Received:2010-04-02 Online:2010-07-16 Published:2010-09-06

Abstract:

In order to solve the problems that the traditional pulse coupled neural network (PCNN) refers only to binary segmentation and does not work well for bigger image regions with sluggish gray variation,a multi-region image segmentation method was proposed based on PCNN. First, the initial image was preprocessed by smoothing and normalizing and put into PCNN. Then, with the help of fast linking, neurons with similar states fired synchronously to finish single region segmentation in each iteration processing. After pre-configured iterations, the total firing times of each neuron were calculated as the pixel intensity of new input image,and then preprocessed by smoothing and normalizing again,and finally put into PCNN. The above processing was repeated to complete multi-region segmentation. Experimental results on Berkeley image database showed that the proposed method was efficient, robust and could be used to segment image effectively.
 

Key words: multi-region segmentation; pulse coupled neural network (PCNN); fast linking

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!