Infrared image segmentation with 2-D maximum entropy method based on particle swarm optimization (PSO)

  • Authors:

  • Du Feng;Shi Wenkang;Chen Liangzhou;Deng Yong;Zhu Zhenfu

  • Affiliations:

  • School of Electronics and Information Technology, Shanghai Jiao Tong University, No. 1954, Huashan Road, Shanghai 200030, People's Republic of China;School of Electronics and Information Technology, Shanghai Jiao Tong University, No. 1954, Huashan Road, Shanghai 200030, People's Republic of China;School of Electronics and Information Technology, Shanghai Jiao Tong University, No. 1954, Huashan Road, Shanghai 200030, People's Republic of China;School of Electronics and Information Technology, Shanghai Jiao Tong University, No. 1954, Huashan Road, Shanghai 200030, People's Republic of China;National Defence Key Laboratory of Target and Environment Feature, Beijing 100854, People's Republic of China

  • Venue:
  • Pattern Recognition Letters
  • Year:
  • 2005

Quantified Score

Hi-index 0.10

Visualization

Abstract

The 2-D maximum entropy method not only considers the distribution of the gray information, but also takes advantage of the spatial neighbor information with using the 2-D histogram of the image. As a global threshold method, it often gets ideal segmentation results even when the image's signal noise ratio (SNR) is low. However, its time-consuming computation is often an obstacle in real time application systems. In this paper, the image thresholding approach based on the index of entropy maximization of the 2-D grayscale histogram is proposed to deal with infrared image. The threshold vector (t,s), where t is a threshold for pixel intensity and s is another threshold for the local average intensity of pixels, is obtained through a new optimization algorithm, namely, the particle swarm optimization (PSO) algorithm. PSO algorithm is realized successfully in the process of solving the 2-D maximum entropy problem. The experiments of segmenting the infrared images are illustrated to show that the proposed method can get ideal segmentation result with less computation cost.