Share Email Print
cover

Proceedings Paper

Infrared image segmentation method based on spatial coherence histogram and maximum entropy
Author(s): Songtao Liu; Tongsheng Shen; Yao Dai
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In order to segment the target well and suppress background noises effectively, an infrared image segmentation method based on spatial coherence histogram and maximum entropy is proposed. First, spatial coherence histogram is presented by weighting the importance of the different position of these pixels with the same gray-level, which is obtained by computing their local density. Then, after enhancing the image by spatial coherence histogram, 1D maximum entropy method is used to segment the image. The novel method can not only get better segmentation results, but also have a faster computation time than traditional 2D histogram-based segmentation methods.

Paper Details

Date Published: 11 November 2014
PDF: 8 pages
Proc. SPIE 9275, Infrared, Millimeter-Wave, and Terahertz Technologies III, 92750U (11 November 2014); doi: 10.1117/12.2071462
Show Author Affiliations
Songtao Liu, Dalian Naval Academy (China)
Tongsheng Shen, China Defense Science and Technology Information Ctr. (China)
Yao Dai, Dalian Naval Academy (China)


Published in SPIE Proceedings Vol. 9275:
Infrared, Millimeter-Wave, and Terahertz Technologies III
Cunlin Zhang; Xi-Cheng Zhang; Masahiko Tani, Editor(s)

© SPIE. Terms of Use
Back to Top