PyFER: A Facial Expression Recognizer Based on Convolutional Neural Networks
Facial expression recognition (FER), one of the most trending research areas of the Human-Machine Interaction, is the task of detecting emotions by analyzing facial expressions and this analysis plays a critical role as it conveys the clearest information regarding the emotions of people. Despite th...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9151954/ |
| _version_ | 1818446169335922688 |
|---|---|
| author | Abdullah Talha Kabakus |
| author_facet | Abdullah Talha Kabakus |
| author_sort | Abdullah Talha Kabakus |
| collection | DOAJ |
| description | Facial expression recognition (FER), one of the most trending research areas of the Human-Machine Interaction, is the task of detecting emotions by analyzing facial expressions and this analysis plays a critical role as it conveys the clearest information regarding the emotions of people. Despite the fact that the traditional machine learning algorithms produce high accuracies for similar tasks, they lack to detect emotions of faces, which are captured in a spontaneous manner (a.k.a. “in the wild”) or in different poses or environmental conditions. In this article, a novel convolutional neural network architecture, namely, PyFER, is proposed to address the FER problem, of which the efficiency was revealed thanks to the experiments conducted on a widely-used benchmark dataset. According to the experimental results, the accuracy of PyFER was calculated to be as high as 96.3% on a de-facto standard dataset, namely, CK +, and all facial expressions, except for $happiness$ , were correctly detected by PyFER, which is encouraging for future studies. 16.67% of the images that actually represented the facial expression happiness were misdetected as the facial expression fear. The experimental results confirmed that the proposed neural network architecture is fast enough to be integrated into real-time FER applications as it was able to complete the analysis of a given photo for an average of 12.8 milliseconds, which is in the tolerable limit to latency for real-time applications. |
| first_indexed | 2024-12-14T19:43:27Z |
| format | Article |
| id | doaj.art-664a94a6d0e34bdbaa921cacd8a3105d |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T19:43:27Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-664a94a6d0e34bdbaa921cacd8a3105d2022-12-21T22:49:38ZengIEEEIEEE Access2169-35362020-01-01814224314224910.1109/ACCESS.2020.30127039151954PyFER: A Facial Expression Recognizer Based on Convolutional Neural NetworksAbdullah Talha Kabakus0https://orcid.org/0000-0003-2181-4292Department of Computer Engineering, Faculty of Engineering, Duzce University, Duzce, TurkeyFacial expression recognition (FER), one of the most trending research areas of the Human-Machine Interaction, is the task of detecting emotions by analyzing facial expressions and this analysis plays a critical role as it conveys the clearest information regarding the emotions of people. Despite the fact that the traditional machine learning algorithms produce high accuracies for similar tasks, they lack to detect emotions of faces, which are captured in a spontaneous manner (a.k.a. “in the wild”) or in different poses or environmental conditions. In this article, a novel convolutional neural network architecture, namely, PyFER, is proposed to address the FER problem, of which the efficiency was revealed thanks to the experiments conducted on a widely-used benchmark dataset. According to the experimental results, the accuracy of PyFER was calculated to be as high as 96.3% on a de-facto standard dataset, namely, CK +, and all facial expressions, except for $happiness$ , were correctly detected by PyFER, which is encouraging for future studies. 16.67% of the images that actually represented the facial expression happiness were misdetected as the facial expression fear. The experimental results confirmed that the proposed neural network architecture is fast enough to be integrated into real-time FER applications as it was able to complete the analysis of a given photo for an average of 12.8 milliseconds, which is in the tolerable limit to latency for real-time applications.https://ieeexplore.ieee.org/document/9151954/Artificial intelligenceartificial neural networksbackpropagationmulti-layer neural networkneural networkssupervised learning |
| spellingShingle | Abdullah Talha Kabakus PyFER: A Facial Expression Recognizer Based on Convolutional Neural Networks IEEE Access Artificial intelligence artificial neural networks backpropagation multi-layer neural network neural networks supervised learning |
| title | PyFER: A Facial Expression Recognizer Based on Convolutional Neural Networks |
| title_full | PyFER: A Facial Expression Recognizer Based on Convolutional Neural Networks |
| title_fullStr | PyFER: A Facial Expression Recognizer Based on Convolutional Neural Networks |
| title_full_unstemmed | PyFER: A Facial Expression Recognizer Based on Convolutional Neural Networks |
| title_short | PyFER: A Facial Expression Recognizer Based on Convolutional Neural Networks |
| title_sort | pyfer a facial expression recognizer based on convolutional neural networks |
| topic | Artificial intelligence artificial neural networks backpropagation multi-layer neural network neural networks supervised learning |
| url | https://ieeexplore.ieee.org/document/9151954/ |
| work_keys_str_mv | AT abdullahtalhakabakus pyferafacialexpressionrecognizerbasedonconvolutionalneuralnetworks |