Exploring polarmetric infrared using classic image computing methods

Author

Grey, Samuel ; Mendoza-Schrock, Olga ; Bourbakis, Nikolaos

Author_Institution

Sch. of Comput. Sci. & Eng., Wright State Univ., Dayton, OH, USA

fYear

2011

fDate

20-22 July 2011

Firstpage

286

Lastpage

290

Abstract

In this paper we apply classic image computing methods to a dataset of passive polarmetric long wave infrared data (LWIR). By employing several different pattern recognition techniques such as k-means clustering, support vector machine (SVM), Naive Bayes, and AdaBoost, we demonstrate accurate classification of skin vs. background with an 84% average classification rate. In addition we explored classification using different polarmetric features such as degree of linear polarization (DoLP), angle of linear polarization (AoLP), and the newly introduced, delta and rho functions.

Keywords

feature extraction; image classification; infrared imaging; pattern clustering; support vector machines; AdaBoost; LWIR; Naive Bayes; SVM; classic image computing methods; k-means clustering; passive polarmetric long wave infrared data; pattern recognition techniques; polarmetric features; support vector machine; Boosting; Educational institutions; Remote sensing; Skin; Support vector machines; Training; Vectors; Infrared (IR); Long Wave Infrared (LWIR); polarization; skin classification;

fLanguage

English

Publisher

ieee

Conference_Titel

Aerospace and Electronics Conference (NAECON), Proceedings of the 2011 IEEE National

Conference_Location

Dayton, OH

ISSN

0547-3578

Print_ISBN

978-1-4577-1040-7

Type

conf

DOI

10.1109/NAECON.2011.6183116

Filename

6183116