Research Article

Facial Expression Recognition of Instructor Using Deep Features and Extreme Learning Machine

Table 7

Accuracy comparison between convolution neural networks on standard datasets along with time taken per frame.

CNN modelJAFFE (%)CK (%)FER2013 (%)Time taken per frame (sec)Number of parameters (million)

AlexNet [86]9390.261.161
VGG16 [86]9692.459.60.94138
VGG19 [87]939360144
ResNet101 [88]904944.5
Inceptionv3 [89]75.876.523
Proposed method96.886.562.50.740.005