Heat-Map Based Emotion and Face Recognition from Thermal Images

Burak Ilikci, Lei Chen, Hyuk Cho, Qingzhong Liu

Research output: Contribution to book or proceedingConference articlepeer-review

12 Scopus citations

Abstract

Nowadays emotion recognition becomes feasible in the Computer Vision domain with the help of Convolutional Neural Networks. However, the credibility of emotion recognition from daily images or videos is evidently insufficient. As people can easily mimic emotions one after another by fooling the computational models, different defensive approaches should be taken into consideration. Particularly, thermal images taken by thermal cameras visualize the facial and body's heat status, revealing where humans actually feel emotions; therefore, models trained with thermal heat-maps are less subject to fake expressions. Accordingly, heat-maps provide suitable resources for developing more credible emotion recognition models. In this paper, a fast detection algorithm, YOLO, is adapted and trained to detect emotions in thermal images. The detection performance, in terms of average precision and intersection over union, from three detection algorithms, YOLO, ResNet, and DenseNet, is compared and their respective characteristics are discussed.

Original languageEnglish
Title of host publication2019 Computing, Communications and IoT Applications, ComComAp 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages449-453
Number of pages5
ISBN (Electronic)9781728119731
DOIs
StatePublished - Oct 2019
Event2019 IEEE International Conference on Computing, Communications and IoT Applications, ComComAp 2019 - Shenzhen, China
Duration: Oct 26 2019Oct 28 2019

Publication series

Name2019 Computing, Communications and IoT Applications, ComComAp 2019

Conference

Conference2019 IEEE International Conference on Computing, Communications and IoT Applications, ComComAp 2019
Country/TerritoryChina
CityShenzhen
Period10/26/1910/28/19

Scopus Subject Areas

  • Computer Networks and Communications
  • Computer Science Applications

Keywords

  • Convolutional Neural Network
  • Emotion recognition
  • Thermal image
  • YOLOv3

Fingerprint

Dive into the research topics of 'Heat-Map Based Emotion and Face Recognition from Thermal Images'. Together they form a unique fingerprint.

Cite this