Automatic Identification of Depression Using Facial Images with Deep Convolutional Neural Network

Xinru Kong; Yan Yao; Cuiying Wang; Yuangeng Wang; Jing Teng; Xianghua Qi

doi:10.12659/MSM.936409

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

Authors information Article notes Copyright and License information

Background Material and Methods Results Discussion Conclusions References

View HTML version

Figure 4 (A–E) Training accuracy vs validation accuracy of FCN, VGG11, VGG19, ResNet50, and Inception-V3. The accuracy of VGG11, ResNet50 network, and Inception-V3 models fluctuated greatly. FCN and VGG19 models had good accuracy. Although the curve of the VGG19 model was relatively flat, the accuracy of the FCN model was significantly improved.

Back to the Article

Automatic Identification of Depression Using Facial Images with Deep Convolutional Neural Network

Your Privacy