A Novel Computational Thermal-Visual Imaging System for Automatic Cornea Temperature Measurement and Tracking
Abstract
Ocular surface temperature (OST) is affected by changes in thephysiology of the eye caused by normal homeostasis, environmental
changes, or systemic and local disease. OST can help a physician
to diagnose eye disease with improved accuracy and provide
useful information for eye research. This paper presents a novel
system including novel hardware design and novel algorithms to
measure and track OST from the cornea automatically over any period
of time. The system uses an IR camera and a visible light camera
to capture synchronous thermal and visible videos, respectively,
from the eye surface. The frames for the two video sequences are
then registered and the cornea was segmented using a semantic
segmentation method. At the final step, the corneal area was localized
on the registered thermal frames to extract temperature information.
The mean square error for the registration was 5.03 ±1.82
and the mean Intersection over Union (IoU) was 94.6%, representing
the accuracy of corneal segmentation. A system for measuring
and tracking eye surface temperature over time was developed. The
system is able to localise the cornea on both visible and thermal images
and report temperature profiles of the cornea over the period
of measurement. Experimental results shows that the whole system
can work as a tool for measuring and tracking OST over time.