Exploring Thermography Technology: A Comprehensive Facial Dataset for Face Detection, Recognition, and Emotion

TL;DR

This paper introduces a comprehensive thermal facial dataset with over 6800 images, supporting research in face detection, recognition, and emotion analysis using thermography technology across various conditions.

Contribution

It provides a large, diverse thermal facial dataset with detailed annotations, facilitating algorithm development, benchmarking, and interdisciplinary research in thermal imaging applications.

Findings

Dataset covers multiple emotions and recognition tasks.

Includes images with varied conditions, angles, and temperature ranges.

Supports advancements in security, healthcare, and HCI applications.

Abstract

This dataset includes 6823 thermal images captured using a UNI-T UTi165A camera for face detection, recognition, and emotion analysis. It consists of 2485 facial recognition images depicting emotions (happy, sad, angry, natural, surprised), 2054 images for face recognition, and 2284 images for face detection. The dataset covers various conditions, color palettes, shooting angles, and zoom levels, with a temperature range of -10{\deg}C to 400{\deg}C and a resolution of 19,200 pixels. It serves as a valuable resource for advancing thermal imaging technology, aiding in algorithm development, and benchmarking for facial recognition across different palettes. Additionally, it contributes to facial motion recognition, fostering interdisciplinary collaboration in computer vision, psychology, and neuroscience. The dataset promotes transparency in thermal face detection and recognition research, with applications in security, healthcare, and human-computer interaction.