Face segmentation: A comparison between visible and thermal images

TL;DR

This paper introduces a face segmentation algorithm tailored for thermal images, demonstrating superior speed and accuracy over the classic Viola-Jones method when applied to multispectral face data.

Contribution

The paper presents a novel face segmentation algorithm specifically designed for thermal images and compares its performance with the Viola-Jones algorithm on multispectral data.

Findings

The proposed algorithm is over 10 times faster than Viola-Jones on multispectral data.

Face segmentation accuracy in thermal images is higher with the proposed method.

The algorithm performs well in multispectral face segmentation tasks.

Abstract

Face segmentation is a first step for face biometric systems. In this paper we present a face segmentation algorithm for thermographic images. This algorithm is compared with the classic Viola and Jones algorithm used for visible images. Experimental results reveal that, when segmenting a multispectral (visible and thermal) face database, the proposed algorithm is more than 10 times faster, while the accuracy of face segmentation in thermal images is higher than in case of Viola-Jones