Litcius/Paper detail

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

202044 citationsDOI

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.

Topics & Concepts

Activation functionSigmoid functionConvolutional neural networkComputer scienceArtificial intelligenceBenchmark (surveying)Hyperbolic functionConvolution (computer science)Pattern recognition (psychology)Contextual image classificationFacial expressionExpression (computer science)Artificial neural networkDeep learningImage (mathematics)MathematicsMathematical analysisGeodesyProgramming languageGeographyFace and Expression RecognitionEmotion and Mood RecognitionFace recognition and analysis