14 May 2017 Mixed features for face detection in thermal image
Author Affiliations +
Proceedings Volume 10338, Thirteenth International Conference on Quality Control by Artificial Vision 2017; 103380E (2017) https://doi.org/10.1117/12.2266836
Event: The International Conference on Quality Control by Artificial Vision 2017, 2017, Tokyo, Japan
Abstract
An infrared (IR) camera captures the temperature distribution of an object as an IR image. Because facial temperature is almost constant, an IR camera has the potential to be used in detecting facial regions in IR images. However, in detecting faces, a simple temperature thresholding does not always work reliably. The standard face detection algorithm used is AdaBoost with local features, such as Haar-like, MB-LBP, and HoG features in the visible images. However, there are few studies using these local features in IR image analysis. In this paper, we propose an AdaBoost-based training method to mix these local features for face detection in thermal images. In an experiment, we captured a dataset from 20 participants, comprising 14 males and 6 females, with 10 variations in camera distance, 21 poses, and participants with and without glasses. Using leave-one-out cross-validation, we show that the proposed mixed features have an advantage over all the regular local features.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Chao Ma, Chao Ma, Ngo Thanh Trung, Ngo Thanh Trung, Hideaki Uchiyama, Hideaki Uchiyama, Hajime Nagahara, Hajime Nagahara, Atsushi Shimada, Atsushi Shimada, Rin-ichiro Taniguchi, Rin-ichiro Taniguchi, } "Mixed features for face detection in thermal image", Proc. SPIE 10338, Thirteenth International Conference on Quality Control by Artificial Vision 2017, 103380E (14 May 2017); doi: 10.1117/12.2266836; https://doi.org/10.1117/12.2266836
PROCEEDINGS
8 PAGES


SHARE
Back to Top