Multiple Convolutional Neural Networks Fusion Using Improved Fuzzy Integral for Facial Emotion Recognition
Facial expressions are indispensable in human cognitive behaviors since it can instantly reveal human emotions. Therefore, in this study, Multiple Convolutional Neural Networks using Improved Fuzzy Integral (MCNNs-IFI) were proposed for recognizing facial emotions. Since effective facial expression...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-06-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/9/13/2593 |
| _version_ | 1818201069613744128 |
|---|---|
| author | Cheng-Jian Lin Chun-Hui Lin Shyh-Hau Wang Chen-Hsien Wu |
| author_facet | Cheng-Jian Lin Chun-Hui Lin Shyh-Hau Wang Chen-Hsien Wu |
| author_sort | Cheng-Jian Lin |
| collection | DOAJ |
| description | Facial expressions are indispensable in human cognitive behaviors since it can instantly reveal human emotions. Therefore, in this study, Multiple Convolutional Neural Networks using Improved Fuzzy Integral (MCNNs-IFI) were proposed for recognizing facial emotions. Since effective facial expression features are difficult to design; deep learning CNN is used in the study. Each CNN has its own advantages and disadvantages, thus combining multiple CNNs can yield superior results. Moreover, multiple CNNs combined with improved fuzzy integral, in which its fuzzy density value is optimized through particle swarm optimization (PSO), overcomes the majority decision drawback in the traditional voting method. Two Multi-PIE and CK+ databases and three main CNN structures, namely AlexNet, GoogLeNet, and LeNet, were used in the experiments. To verify the results, a cross-validation method was used, and experimental results indicated that the proposed MCNNs-IFI exhibited 12.84% higher accuracy than that of the three CNNs. |
| first_indexed | 2024-12-12T02:47:42Z |
| format | Article |
| id | doaj.art-82d6e1b39008421ab879a93138d4c621 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-12T02:47:42Z |
| publishDate | 2019-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-82d6e1b39008421ab879a93138d4c6212022-12-22T00:40:58ZengMDPI AGApplied Sciences2076-34172019-06-01913259310.3390/app9132593app9132593Multiple Convolutional Neural Networks Fusion Using Improved Fuzzy Integral for Facial Emotion RecognitionCheng-Jian Lin0Chun-Hui Lin1Shyh-Hau Wang2Chen-Hsien Wu3Department of Computer Science and Information Engineering, National Chin-Yi University of Technology, Taichung City 411, TaiwanDepartment of Computer Science & Information Engineering Nation Cheng Kung University, Tainan 701, TaiwanDepartment of Computer Science & Information Engineering Nation Cheng Kung University, Tainan 701, TaiwanDepartment of Computer Science and Information Engineering, National Chin-Yi University of Technology, Taichung City 411, TaiwanFacial expressions are indispensable in human cognitive behaviors since it can instantly reveal human emotions. Therefore, in this study, Multiple Convolutional Neural Networks using Improved Fuzzy Integral (MCNNs-IFI) were proposed for recognizing facial emotions. Since effective facial expression features are difficult to design; deep learning CNN is used in the study. Each CNN has its own advantages and disadvantages, thus combining multiple CNNs can yield superior results. Moreover, multiple CNNs combined with improved fuzzy integral, in which its fuzzy density value is optimized through particle swarm optimization (PSO), overcomes the majority decision drawback in the traditional voting method. Two Multi-PIE and CK+ databases and three main CNN structures, namely AlexNet, GoogLeNet, and LeNet, were used in the experiments. To verify the results, a cross-validation method was used, and experimental results indicated that the proposed MCNNs-IFI exhibited 12.84% higher accuracy than that of the three CNNs.https://www.mdpi.com/2076-3417/9/13/2593Facial emotion recognitionconvolutional neural networkfuzzy integralparticle swarm optimization |
| spellingShingle | Cheng-Jian Lin Chun-Hui Lin Shyh-Hau Wang Chen-Hsien Wu Multiple Convolutional Neural Networks Fusion Using Improved Fuzzy Integral for Facial Emotion Recognition Applied Sciences Facial emotion recognition convolutional neural network fuzzy integral particle swarm optimization |
| title | Multiple Convolutional Neural Networks Fusion Using Improved Fuzzy Integral for Facial Emotion Recognition |
| title_full | Multiple Convolutional Neural Networks Fusion Using Improved Fuzzy Integral for Facial Emotion Recognition |
| title_fullStr | Multiple Convolutional Neural Networks Fusion Using Improved Fuzzy Integral for Facial Emotion Recognition |
| title_full_unstemmed | Multiple Convolutional Neural Networks Fusion Using Improved Fuzzy Integral for Facial Emotion Recognition |
| title_short | Multiple Convolutional Neural Networks Fusion Using Improved Fuzzy Integral for Facial Emotion Recognition |
| title_sort | multiple convolutional neural networks fusion using improved fuzzy integral for facial emotion recognition |
| topic | Facial emotion recognition convolutional neural network fuzzy integral particle swarm optimization |
| url | https://www.mdpi.com/2076-3417/9/13/2593 |
| work_keys_str_mv | AT chengjianlin multipleconvolutionalneuralnetworksfusionusingimprovedfuzzyintegralforfacialemotionrecognition AT chunhuilin multipleconvolutionalneuralnetworksfusionusingimprovedfuzzyintegralforfacialemotionrecognition AT shyhhauwang multipleconvolutionalneuralnetworksfusionusingimprovedfuzzyintegralforfacialemotionrecognition AT chenhsienwu multipleconvolutionalneuralnetworksfusionusingimprovedfuzzyintegralforfacialemotionrecognition |