Empirical Evaluation of Activation Functions in Deep Convolution Neural Network for Facial Expression Recognition
Muhammad Irfan Khalid, Junaid Baber, Mumraiz Khan Kasi, Maheen Bakhtyar, Varsha Devi, Naveed Sheikh
Abstract
Deep Convolutional Neural Network (DCNN) is widely used as state-of-the art models for image classification. There is a variety of applications related to image classification such as object classification, facial expression classification, and scene classification. In this paper, different activation functions are evaluated for facial expression recognition (FER). The activation functions used for evaluation are Rectified Linear Unit (ReLU), Leaky Rectified Linear Unit (Leaky ReLU), Hyperbolic Tangent Tanh, and Sigmoid. Experiments are conducted on a benchmark dataset known as Fer2013 which is publicly available on Kaggle. Our experiments show that Tanh achieved better performance compared to other activation functions.