KJCKorea
Journal Central

@article{ART002794937},
author={Lee Donghwan and Jang-Hee Yoo},
title={Divide and Conquer Strategy for CNN model in Facial Emotion Recognition based on Thermal Images},
journal={Journal of Software Assessment and Valuation},
issn={2092-8114},
year={2021},
volume={17},
number={2},
pages={1-10},
doi={10.29056/jsav.2021.12.01}

TY - JOUR
AU - Lee Donghwan
AU - Jang-Hee Yoo
TI - Divide and Conquer Strategy for CNN model in Facial Emotion Recognition based on Thermal Images
JO - Journal of Software Assessment and Valuation
PY - 2021
VL - 17
IS - 2
PB - Korea Software Assessment and Valuation Society
SP - 1
EP - 10
SN - 2092-8114
AB - The ability to recognize human emotions by computer vision is a very important task, with many potential applications. Therefore the demand for emotion recognition using not only RGB images but also thermal images is increasing. Compared to RGB images, thermal images has the advantage of being less affected by lighting conditions but require a more sophisticated recognition method with low-resolution sources. In this paper, we propose a Divide and Conquer-based CNN training strategy to improve the performance of facial thermal image-based emotion recognition. The proposed method first trains to classify difficult-to-classify similar emotion classes into the same class group by confusion matrix analysis and then divides and solves the problem so that the emotion group classified into the same class group is recognized again as actual emotions. In experiments, the proposed method has improved accuracy in all the tests than when recognizing all the presented emotions with a single CNN model.
KW - Facial emotion recognition;Thermal image;CNN training strategy;Divide and Conquer
DO - 10.29056/jsav.2021.12.01
ER -

Lee Donghwan and Jang-Hee Yoo. (2021). Divide and Conquer Strategy for CNN model in Facial Emotion Recognition based on Thermal Images. Journal of Software Assessment and Valuation, 17(2), 1-10.

Lee Donghwan and Jang-Hee Yoo. 2021, "Divide and Conquer Strategy for CNN model in Facial Emotion Recognition based on Thermal Images", Journal of Software Assessment and Valuation, vol.17, no.2 pp.1-10. Available from: doi:10.29056/jsav.2021.12.01

Lee Donghwan, Jang-Hee Yoo "Divide and Conquer Strategy for CNN model in Facial Emotion Recognition based on Thermal Images" Journal of Software Assessment and Valuation 17.2 pp.1-10 (2021) : 1.

Lee Donghwan, Jang-Hee Yoo. Divide and Conquer Strategy for CNN model in Facial Emotion Recognition based on Thermal Images. 2021; 17(2), 1-10. Available from: doi:10.29056/jsav.2021.12.01

Lee Donghwan and Jang-Hee Yoo. "Divide and Conquer Strategy for CNN model in Facial Emotion Recognition based on Thermal Images" Journal of Software Assessment and Valuation 17, no.2 (2021) : 1-10.doi: 10.29056/jsav.2021.12.01

Lee Donghwan; Jang-Hee Yoo. Divide and Conquer Strategy for CNN model in Facial Emotion Recognition based on Thermal Images. Journal of Software Assessment and Valuation, 17(2), 1-10. doi: 10.29056/jsav.2021.12.01

Lee Donghwan; Jang-Hee Yoo. Divide and Conquer Strategy for CNN model in Facial Emotion Recognition based on Thermal Images. Journal of Software Assessment and Valuation. 2021; 17(2) 1-10. doi: 10.29056/jsav.2021.12.01

Lee Donghwan, Jang-Hee Yoo. Divide and Conquer Strategy for CNN model in Facial Emotion Recognition based on Thermal Images. 2021; 17(2), 1-10. Available from: doi:10.29056/jsav.2021.12.01

Lee Donghwan and Jang-Hee Yoo. "Divide and Conquer Strategy for CNN model in Facial Emotion Recognition based on Thermal Images" Journal of Software Assessment and Valuation 17, no.2 (2021) : 1-10.doi: 10.29056/jsav.2021.12.01