Sarvenaz Ghafourian, Ramin Sharifi and Amirali Baniasadi, University of Victoria, Canada

The wide usage of computer vision has become popular in the recent years. One of the areas of computer vision that has been studied is facial emotion recognition, which plays a crucial role in the interpersonal communication. This paper tackles the problem of intraclass variances in the face images of emotion recognition datasets. We test the system on augmented datasets including CK+, EMOTIC, and KDEF dataset samples. After modifying our dataset, using SMOTETomek approach, we observe improvement over the default method.

Emotion Recognition, Residual Network, VGG.