IAES International Journal of Artificial Intelligence (IJ-AI) Vol. 11, No. 4, December 2022, pp. 1478~1486 ISSN: 2252-8938, DOI: 10.11591/ ija i.v 11.i4.pp1478-1486  1478 Journal homepage: http://ijai.iaescore.com Classification technique for real-time emotion detection using machine learning models Chanathip Sawangwong 1 , Kritsada Puangsuwan 1 , Nathaphon Boonnam 1 , Siriwan Kajornkasirat 1 , Wacharapong Srisang 2 1 Faculty of Science and Industrial Technology, Prince of Songkla University, Surat Thani Campus, Surat Thani, Thailand 2 Faculty of Science and Agricultural Technology, Rajamangala University of Technology Lanna, Lampang, Thailand Article Info ABSTRACT Article history: Received Dec 16, 2021 Revised Jul 8, 2022 Accepted Aug 6, 2022 This study aimed to explore models to identify a human by using face recognition techniques. Data were collected from Cohn-Kanade dataset composed of 398 photos having face emotion labeled with eight emotions (i.e., neutral, angry, disgusted, fearful, happy, sad, and surprised). M ulti- layer perceptron (M LP), support vector machine (SVM ), and random forest were used in model accuracy comparisons. Model validation and evaluation were performed using Python programming. The results on F1 scores for each class in the dataset revealed that predictive classifiers do not perform well for some classes. The support vector machine (RBF kernel) and random forest showed the highest accuracies in both datasets. The results could be used to extract and identify emotional expressions from the Cohn-Kanade dataset. Furthermore, the approach could be applied in other contexts to enhance monitoring activities or facial assessments. Keywords: Classification Emotion detection Image processing Machine learning This is an open access article under the CC BY-SA license. Corresponding Author: Kritsada Puangsuwan Faculty of Science and Industrial Technology, Prince of Songkla University Surat Thani Campus, 31 Moo 6, Makhamtia, Muang, Surat Thani 84000, Thailand Email: kritsada.pu@psu.ac.th 1. INTRODUCTION Emotion recognition is being actively researched in various fields, including computer science, neurology, biology, psychology, and medicine, both in theory and in applications [1]. It is a crucial step towards machines that understand human behavior. Anger, disgust, contempt, fear, joy, sadness, neutrality and surprise are the eight basic human emotions. There are several ways to recognize human emotions using various human behavioral features such as speech, electroencephalogram (EEG) data, and facial images [2]. Machine learning is a topic of study that focuses on how to turn empirical data into useable models using computational techniques. Traditional statistics and artificial intelligence groups gave birth to the machine learning discipline [3]. Machine learning can be divided into three types, namely supervised learning (learning with data to teach), unsupervised learning (learning without teaching data), and reinforcement learning (learning according to the environment). Emotion recognition from video requires the functions of face recognition. Face recognition is a technology capable of matching a human face from a digital image or a video frame against a database of faces, typically employed to authenticate users through ID verification services, and it works by pinpointing and measuring facial features from a given image. Face recognition can be applied in many contexts, of which we list a few. (i) Access Control: The size of the group of people who need to be identified in many access control applications, such as office access or computer logon, is rather modest. Face images are also captured in natural settings, such as frontal faces with indoors lighting for office door access control [4].