[Retracted] Facial Expression Recognition Based on Convolutional Neural Network Fusion SIFT Features of Mobile Virtual Reality

Table 1

Convolutional network parameters.

Layer	Type	Kernel size ()	Stride	Output number	Output size ()
Layer1	Convolution		1	64
Layer2	Convolution		1	128
Layer3	Max pooling		2	128
Layer4	Convolution		1	128
Layer5	Convolution		1	128
Layer6	Convolution		1	256
Layer7	Max pooling		2	256
Layer8	Convolution		1	256
Layer9	Convolution		1	256
Layer10	Average pooling		3	256
Layer11	Convolution		1	512
Layer12	Fully connected	—	—	—
Output	SoftMax	—	—	—