Using CNN for facial expression recognition: a study of the effects of kernel size and number of filters on accuracy

• Published in: The Visual computer Vol. 36; no. 2; pp. 405 - 412
• Main Authors: Agrawal, Abhinav, Mittal, Namita
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.02.2020; Springer Nature B.V
• Subjects: Accuracy; Artificial Intelligence; Artificial neural networks; Classification; Computer Graphics; Computer Science; Data processing; Datasets; Deep learning; Face recognition; Image classification; Image Processing and Computer Vision; Machine learning; Neural networks; Original Article; Deep learning; FER-2013; CNN
• ISSN: 0178-2789; 1432-2315
• DOI: 10.1007/s00371-019-01630-9

Facial expression recognition is a challenging problem in image classification. Recently, the use of deep learning is gaining importance in image classification. This has led to increased efforts in solving the problem of facial expression recognition using convolutional neural networks (CNNs). A significant challenge in deep learning is to design a network architecture that is simple and effective. A simple architecture is fast to train and easy to implement. An effective architecture achieves good accuracy on the test data. CNN architectures are black boxes to us. VGGNet, AlexNet and Inception are well-known CNN architectures. These architectures have strongly influenced CNN model designs for new datasets. Almost all CNN models known to achieve high accuracy on facial expression recognition problem are influenced by these architectures. This work tries to overcome this limitation by using FER-2013 dataset as starting point to design new CNN models. In this work, the effect of CNN parameters namely kernel size and number of filters on the classification accuracy is investigated using FER-2013 dataset. Our major contribution is a thorough evaluation of different kernel sizes and number of filters to propose two novel CNN architectures which achieve a human-like accuracy of 65% (Goodfellow et al. in: Neural information processing, Springer, Berlin, pp 117–124, 2013 ) on FER-2013 dataset. These architectures can serve as a basis for standardization of the base model for the much inquired FER-2013 dataset.