Inner-Canthus Localization of Thermal Images in Face-View Invariant

Abstract

Inner-canthus localization has played an essential role in measuring human body temperature. This is due to the theory that human core body temperature can be measured in the inner-canthus. Such measurement is useful for mass screening since it is non-contact, non-invasive and fast. This paper presents an algorithm that has been developed to locate the inner-canthus. The algorithm proposed a robust method in various face-view, i.e., frontal, sided and tilted. The algorithm consisted of: face segmentation, determining face-orientation, rotating face into straight view, eye localization, and inner-canthus localization. The face segmentation used human temperature threshold of 34°C-the face orientation used trend line of a middle point between each most-bottom and most-top coordinates. The face rotation was based on the gradient of the trend line. Once the face is rotated, the eye location was determined using facial proportion. The inner-canthus location was determined as the highest intensities in the eye-frame. The test on 15 thermal images of faces with various view showed localization accuracy of 80% for eye-frame determination and 100% for innercanthus localization.

Automatic Measurement of Human Body Temperature on Thermal Image Using Knowledge-Based Criteria

“…The face must not wearing glasses since the inner-canthus would be covered and infrared could not transmit through glass. Images were acquired using thermal infrared camera with locked range of temperature of 26 C -37 C. Face detection algorithm for infrared images has been explained in [8] which used human temperature as threshold. The seg-mented face from background is shown in Fig.1(a).…”

Eye Recognition by YOLO for Inner Canthus Temperature Detection in the Elderly Using a Transfer Learning Approach

“…However, this algorithm lacks reliability in cases of longer face height and in cases of neck presence in the image, for example, which resulted in an error in proportions. Accordingly, the eye frame will not be correctly localized, causing incorrect inner canthus detection [ 13 ]. Additionally, Knapik et al, in their paper entitled “Fast Eyes Detection in Thermal Images”, presented a pre-processing image technique that mainly converts the low-dynamic range thermal image into a high-dynamic range image for detail enhancement followed by the use of scale-invariant feature transform (SIFT).…”

Detecting Essential Landmarks Directly in Thermal Images for Remote Body Temperature and Respiratory Rate Measurement With a Two-Phase System

“…Fitriyah et al [31] detected the inner canthi by finding a collection of blobs, two of which contain the inner canthi, but the results revealed that their knowledge-based criteria falsely identified non-canthi points. Another study [32] located the inner canthi in thermal images of people whose heads were tilted and rotated at different angles, but when eye localization was performed inside the face bounding box, the presence of a subject's neck in the box could affect the system's ability to locate their canthi. Berlincioni et al [33] proposed an automated method for localizing inner canthi in thermal images by using the OpenPose detector to estimate coarse canthi locations which were refined using a 3D Morphable Face Model.…”