10 July 2022>: Clinical Research
Automatic Identification of Depression Using Facial Images with Deep Convolutional Neural Network
Xinru Kong 1CE* , Yan Yao 1BC* , Cuiying Wang 1BC , Yuangeng Wang 1BF , Jing Teng 2DG , Xianghua Qi 2AG*DOI: 10.12659/MSM.936409
Med Sci Monit 2022; 28:e936409
Table 1 Accuracy, precision, recall and F1 score of each model. FCN model achieved good results in Accuracy, precision, recall and F1. The VGG19 model had good accuracy and precision. The Inception-V3 model was behind the FCN model on recall and F1.
Model | Accuracy (%) | Precision (%) | Recall (%) | F1(%) |
---|---|---|---|---|
FNC | 98.23 | 98.11 | 98.16 | 98.27 |
Vgg11 | 94.40 | 96.15 | 92.02 | 94.04 |
Vgg19 | 97.35 | 98.13 | 96.32 | 97.21 |
ResNet50 | 94.99 | 98.03 | 91.41 | 94.60 |
Inception-V3 | 97.10 | 96.20 | 98.79 | 98.19 |