Share Email Print

Proceedings Paper

Intelligent multi-spectral IR image segmentation
Author(s): Thomas Lu; Andrew Luong; Stephen Heim; Maharshi Patel; Kang Chen; Tien-Hsin Chao; Edward Chow; Gilbert Torres
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This article presents a neural network based multi-spectral image segmentation method. A neural network is trained on the selected features of both the objects and background in the longwave (LW) Infrared (IR) images. Multiple iterations of training are performed until the accuracy of the segmentation reaches satisfactory level. The segmentation boundary of the LW image is used to segment the midwave (MW) and shortwave (SW) IR images. A second neural network detects the local discontinuities and refines the accuracy of the local boundaries. This article compares the neural network based segmentation method to the Wavelet-threshold and Grab-Cut methods. Test results have shown increased accuracy and robustness of this segmentation scheme for multi-spectral IR images.

Paper Details

Date Published: 1 May 2017
PDF: 11 pages
Proc. SPIE 10203, Pattern Recognition and Tracking XXVIII, 1020303 (1 May 2017); doi: 10.1117/12.2262730
Show Author Affiliations
Thomas Lu, Jet Propulsion Lab. (United States)
Andrew Luong, Univ. of California, Irvine (United States)
Stephen Heim, Occidental College (United States)
Maharshi Patel, Univ. of California, Irvine (United States)
Kang Chen, Univ. of California, Los Angeles (United States)
Tien-Hsin Chao, Jet Propulsion Lab. (United States)
Edward Chow, Jet Propulsion Lab. (United States)
Gilbert Torres, Naval Air Warfare Ctr. Weapons Div. (United States)

Published in SPIE Proceedings Vol. 10203:
Pattern Recognition and Tracking XXVIII
Mohammad S. Alam, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?