Table 3 Classification accuracies summary
Paper name | Dataset | Method | Accuracy rate (%) |
|---|---|---|---|
Facial emotion recognition: state of the art performance on FER2013 [8] | FER2013 | VGG13 | 73.28 |
Automatic prediction of depression and anxiety [18] | FER2013 | CNN | 63 |
Local learning to improve bag of visual words model for facial expression recognition [26] | JAFFE + (CK+) + MMI | Bag of word | 67.484 |
Deep learning approaches for facial emotion recognition: a case study on FER-2013 [21] | FER2013 | GooglelNet | 65.2 |
Local learning with deep and handcrafted features for facial expression recognition [27] | FER+ | VGG-SVM | 66.31 |
Going deeper in facial expression recognition using deep neural networks [28] | (CK+) + DISFA, + FER | Conv + inception layer | 66.4 |
Learning to amend facial expression representation via de-albino and affinity [29] | RAF-DB + AffectNet + SFEW | ARM(ResNet-18) | 71.28 |
Facial expression recognition using convolutional neural networks: state of the art [30] | FER+ | ResNet | 72.2 |
| Â | Â | VGG | 72.7 |
The proposed model | FER++ (CK+) | VGG | 95 |