Publication

Abstract : Facial emotion recognition plays a crucial role in human-computer interaction and artificial intelligence applications, serving as a cornerstone for understanding user emotions. The accurate interpretation of facial expressions is particularly vital in domains such as virtual assistants, human-computer interfaces, and emotion-aware technologies, allowing systems to respond precisely and tailor interactions based on the user’s emotional state. In order to overcome challenges associated with conventional approaches, this study introduces the FacialEmoNet technique, an innovative algorithm that seamlessly integrates deep learning and machine learning methods for the efficient classification of facial expression datasets. The primary focus is on capturing and interpreting facial expressions, marking its efficacy and significant advancement in emotion recognition systems. This work investigates the utilization of existing classifiers to classify the dataset effectively. FacialEmoNet utilizes a dynamic methodology to improve recognition accuracy by implementing pioneering feature extraction techniques, resulting in an impressive accuracy of 97.56% and an exceptionally low error rate of 2.44%.