Inner Eye Canthus Localization for Human Body Temperature Screening

TL;DR

This paper introduces an automatic method for accurately locating the inner eye canthus in thermal face images to improve body temperature screening, utilizing facial keypoints, 3D face modeling, and dataset augmentation.

Contribution

It presents a novel approach combining facial keypoint detection and 3D morphable models for precise eye canthus localization, along with an enriched, annotated thermal face dataset.

Findings

Effective localization of inner eye canthus in thermal images

Enhanced dataset with 3D head poses and occlusion masks

Potential for improved temperature measurement accuracy

Abstract

In this paper, we propose an automatic approach for localizing the inner eye canthus in thermal face images. We first coarsely detect 5 facial keypoints corresponding to the center of the eyes, the nosetip and the ears. Then we compute a sparse 2D-3D points correspondence using a 3D Morphable Face Model (3DMM). This correspondence is used to project the entire 3D face onto the image, and subsequently locate the inner eye canthus. Detecting this location allows to obtain the most precise body temperature measurement for a person using a thermal camera. We evaluated the approach on a thermal face dataset provided with manually annotated landmarks. However, such manual annotations are normally conceived to identify facial parts such as eyes, nose and mouth, and are not specifically tailored for localizing the eye canthus region. As additional contribution, we enrich the original dataset by using the annotated landmarks to deform and project the 3DMM onto the images. Then, by manually selecting a small region corresponding to the eye canthus, we enrich the dataset with additional annotations. By using the manual landmarks, we ensure the correctness of the 3DMM projection, which can be used as ground-truth for future evaluations. Moreover, we supply the dataset with the 3D head poses and per-point visibility masks for detecting self-occlusions. The data will be publicly released.