Journal
PATTERN RECOGNITION LETTERS
Volume 120, Issue -, Pages 69-74Publisher
ELSEVIER
DOI: 10.1016/j.patrec.2019.01.008
Keywords
Facial emotion recognition; Deep neural network; Fully convolution network
Categories
Ask authors/readers for more resources
Humans use facial expressions to show their emotional states. However, facial expression recognition has remained a challenging and interesting problem in computer vision. In this paper we present our approach which is the extension of our previous work for facial emotion recognition [1]. The aim of this work is to classify each image into one of six facial emotion classes. The proposed model is based on single Deep Convolutional Neural Networks (DNNs), which contain convolution layers and deep residual blocks. In the proposed model, firstly the image label to all faces has been set for the training. Secondly, the images go through proposed DNN model. This model trained on two datasets Extended Cohn-Kanade (CK+) and Japanese Female Facial Expression (JAFFE) Dataset. The overall results show that, the proposed DNN model can outperform the recent state-of-the-art approaches for emotion recognition. Even the proposed model has accuracy improvement in comparison with our previous model. (C) 2019 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available