Abstract: Facial Emotion Recognition (FER) is a significant technology in fields such as human-computer interaction, healthcare, and security. This paper investigates the use of Convolutional Neural Networks (CNNs) for improving the accuracy and reliability of FER systems. CNNs, known for their ability to automatically extract hierarchical features from raw data, offer substantial improvements over traditional machine learning techniques. The proposed system is trained on a large dataset of facial images and demonstrates a notable improvement in accuracy, achieving a classification rate of 93.5% across multiple emotion categories. The study also includes a comprehensive literature survey, examining key advancements in FER and the role of CNNs in this domain.

Keywords: Facial Emotion Recognition, Convolutional Neural Networks, Deep Learning, Emotion Detection, Human-Computer Interaction

| DOI: 10.17148/IARJSET.2024.11828