On Classification of the Human Emotions from Facial Thermal Images: A Case Study Based on Machine Learning
(1) Background: This paper intends to accomplish a comparative study and analysis regarding the multiclass classification of facial thermal images, i.e., in three classes corresponding to predefined emotional states (neutral, happy and sad). By carrying out a comparative analysis, the main goal of t...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Machine Learning and Knowledge Extraction |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-4990/7/2/27 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850168389132091392 |
|---|---|
| author | Marius Sorin Pavel Simona Moldovanu Dorel Aiordachioaie |
| author_facet | Marius Sorin Pavel Simona Moldovanu Dorel Aiordachioaie |
| author_sort | Marius Sorin Pavel |
| collection | DOAJ |
| description | (1) Background: This paper intends to accomplish a comparative study and analysis regarding the multiclass classification of facial thermal images, i.e., in three classes corresponding to predefined emotional states (neutral, happy and sad). By carrying out a comparative analysis, the main goal of the paper consists in identifying a suitable algorithm from machine learning field, which has the highest accuracy (ACC). Two categories of images were used in the process, i.e., images with Gaussian noise and images with “salt and pepper” type noise that come from two built-in special databases. An augmentation process was applied to the initial raw images that led to the development of the two databases with added noise, as well as the subsequent augmentation of all images, i.e., rotation, reflection, translation and scaling. (2) Methods: The multiclass classification process was implemented through two subsets of methods, i.e., machine learning with random forest (RF), support vector machines (SVM) and k-nearest neighbor (KNN) algorithms and deep learning with the convolutional neural network (CNN) algorithm. (3) Results: The results obtained in this paper with the two subsets of methods belonging to the field of artificial intelligence (AI), together with the two categories of facial thermal images with added noise used as input, were very good, showing a classification accuracy of over 99% for the two categories of images, and the three corresponding classes for each. (4) Discussion: The augmented databases and the additional configurations of the implemented algorithms seems to have had a positive effect on the final classification results. |
| format | Article |
| id | doaj-art-8b4095e4d8da450ead706e9857675a22 |
| institution | OA Journals |
| issn | 2504-4990 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machine Learning and Knowledge Extraction |
| spelling | doaj-art-8b4095e4d8da450ead706e9857675a222025-08-20T02:20:58ZengMDPI AGMachine Learning and Knowledge Extraction2504-49902025-03-01722710.3390/make7020027On Classification of the Human Emotions from Facial Thermal Images: A Case Study Based on Machine LearningMarius Sorin Pavel0Simona Moldovanu1Dorel Aiordachioaie2Department of Electronics and Telecommunications, Faculty of Automation, Computers, Electrical Engineering and Electronics, Dunarea de Jos University of Galati, 47 Domneasca Street, 800008 Galati, RomaniaDepartment of Computer Science and Information Technology, Faculty of Automation, Computers, Electrical Engineering and Electronics, Dunarea de Jos University of Galati, 47 Domneasca Street, 800008 Galati, RomaniaDepartment of Electronics and Telecommunications, Faculty of Automation, Computers, Electrical Engineering and Electronics, Dunarea de Jos University of Galati, 47 Domneasca Street, 800008 Galati, Romania(1) Background: This paper intends to accomplish a comparative study and analysis regarding the multiclass classification of facial thermal images, i.e., in three classes corresponding to predefined emotional states (neutral, happy and sad). By carrying out a comparative analysis, the main goal of the paper consists in identifying a suitable algorithm from machine learning field, which has the highest accuracy (ACC). Two categories of images were used in the process, i.e., images with Gaussian noise and images with “salt and pepper” type noise that come from two built-in special databases. An augmentation process was applied to the initial raw images that led to the development of the two databases with added noise, as well as the subsequent augmentation of all images, i.e., rotation, reflection, translation and scaling. (2) Methods: The multiclass classification process was implemented through two subsets of methods, i.e., machine learning with random forest (RF), support vector machines (SVM) and k-nearest neighbor (KNN) algorithms and deep learning with the convolutional neural network (CNN) algorithm. (3) Results: The results obtained in this paper with the two subsets of methods belonging to the field of artificial intelligence (AI), together with the two categories of facial thermal images with added noise used as input, were very good, showing a classification accuracy of over 99% for the two categories of images, and the three corresponding classes for each. (4) Discussion: The augmented databases and the additional configurations of the implemented algorithms seems to have had a positive effect on the final classification results.https://www.mdpi.com/2504-4990/7/2/27thermal imagesemotional states recognitionmachine learningdeep learningdatabase expansion techniquesmulticlass classification |
| spellingShingle | Marius Sorin Pavel Simona Moldovanu Dorel Aiordachioaie On Classification of the Human Emotions from Facial Thermal Images: A Case Study Based on Machine Learning Machine Learning and Knowledge Extraction thermal images emotional states recognition machine learning deep learning database expansion techniques multiclass classification |
| title | On Classification of the Human Emotions from Facial Thermal Images: A Case Study Based on Machine Learning |
| title_full | On Classification of the Human Emotions from Facial Thermal Images: A Case Study Based on Machine Learning |
| title_fullStr | On Classification of the Human Emotions from Facial Thermal Images: A Case Study Based on Machine Learning |
| title_full_unstemmed | On Classification of the Human Emotions from Facial Thermal Images: A Case Study Based on Machine Learning |
| title_short | On Classification of the Human Emotions from Facial Thermal Images: A Case Study Based on Machine Learning |
| title_sort | on classification of the human emotions from facial thermal images a case study based on machine learning |
| topic | thermal images emotional states recognition machine learning deep learning database expansion techniques multiclass classification |
| url | https://www.mdpi.com/2504-4990/7/2/27 |
| work_keys_str_mv | AT mariussorinpavel onclassificationofthehumanemotionsfromfacialthermalimagesacasestudybasedonmachinelearning AT simonamoldovanu onclassificationofthehumanemotionsfromfacialthermalimagesacasestudybasedonmachinelearning AT dorelaiordachioaie onclassificationofthehumanemotionsfromfacialthermalimagesacasestudybasedonmachinelearning |