Live Emotion Detection Using Deepface

In numerous applications, including security, human-computer interface, road safety, and healthcare, real-time emotion detection is essential. This academic paper describes a Python-based investigation on real-time emotion recognition. The goal is to use computer vision and machine learning techniques to automatically detect facial expressions and identify emotions in real-time. The Deepface package is used as the main tool in this investigation because of its capability for facial matching and emotion recognition. This study uses Python's Deepface library to investigate real-time emotion recognition. It starts with a thorough study of the literature, looking at earlier investigations into the identification of facial expressions and emotions. The emotion-detection classifier is trained using the Extended Cohn-Kanade (CK+) dataset, which includes a variety of facial expressions. The technique section covers the selected strategy, which makes use of Deepface and incorporates models for facial detection and processing such VGG-Face, ArcFace, and Dlib. The performance ratings of various models, as determined by LFW and YTF measures, are displayed in experimental findings. The results underline the efficacy of real-time emotion recognition and the capability of computer vision and machine learning for precise facial expression analysis. Enhancing model performance for real-world circumstances can be the subject of future research.