An Android Application for Facial Expression Recognition Using Deep Learning

Abstract

Facial expression recognition (FER) is one of the most popular research interests in Computer Science and can be applied in many real time applications. Most of the FER systems apply machine learning techniques such as Convolutional Neural Network and Support Vector Machine. Although there are many researches on recognition of facial expression, it is still a challenging task for computer programs and also mobile applications. Therefore, this paper proposed an Android application for FER using deep learning technique that can recognize three facial expressions which are happy, angry and surprise. FER model has been trained by using Personal Image Classifier (PIC) based on facial expression dataset from Kaggle and achieved 95% accuracy. The trained model was later applied for Android application development in MIT App Inventor. The proposed Android application for FER has been successfully built, tested, and uploaded into Google Play Store.