BP network identification technology of infrared polarization based on fuzzy c-means clustering

Haifang Zeng; Guohua Gu; Weiji He; Qian Chen; Wei Yang

doi:10.1117/12.900239

8 September 2011 BP network identification technology of infrared polarization based on fuzzy c-means clustering

Haifang Zeng, Guohua Gu, Weiji He, Qian Chen, Wei Yang

Proceedings Volume 8193, International Symposium on Photoelectronic Detection and Imaging 2011: Advances in Infrared Imaging and Applications; 81931Z (2011) https://doi.org/10.1117/12.900239
Event: International Symposium on Photoelectronic Detection and Imaging 2011, 2011, Beijing, China

Abstract

Infrared detection system is frequently employed on surveillance operations and reconnaissance mission to detect particular targets of interest in both civilian and military communities. By incorporating the polarization of light as supplementary information, the target discrimination performance could be enhanced. So this paper proposed an infrared target identification method which is based on fuzzy theory and neural network with polarization properties of targets. The paper utilizes polarization degree and light intensity to advance the unsupervised KFCM (kernel fuzzy C-Means) clustering method. And establish different material pol1arization properties database. In the built network, the system can feedback output corresponding material types of probability distribution toward any input polarized degree such as 10° 15°, 20°, 25°, 30°. KFCM, which has stronger robustness and accuracy than FCM, introduces kernel idea and gives the noise points and invalid value different but intuitively reasonable weights. Because of differences in characterization of material properties, there will be some conflicts in classification results. And D - S evidence theory was used in the combination of the polarization and intensity information. Related results show KFCM clustering precision and operation rate are higher than that of the FCM clustering method. The artificial neural network method realizes material identification, which reasonable solved the problems of complexity in environmental information of infrared polarization, and improperness of background knowledge and inference rule. This method of polarization identification is fast in speed, good in self-adaption and high in resolution.

Citation Download Citation

Haifang Zeng, Guohua Gu, Weiji He, Qian Chen, and Wei Yang "BP network identification technology of infrared polarization based on fuzzy c-means clustering", Proc. SPIE 8193, International Symposium on Photoelectronic Detection and Imaging 2011: Advances in Infrared Imaging and Applications, 81931Z (8 September 2011); https://doi.org/10.1117/12.900239

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
9 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Polarization

Infrared radiation

Image fusion

Infrared imaging

Iron

Neural networks

Image processing

Show All Keywords

Keywords/Phrases

Search In:

Publication Years