Emotion Classification using Artificial Neural Networks and Haar Cascade

This research work proposes a real-time emotion recognition system utilizing Artificial Neural Networks (ANN) and Haar cascades for facial feature detection. Initially Lumed-2 dataset is used for training and modeling. Emotion recognition plays a pivotal role in human-computer interaction, affective computing, and various other domains. The system aims to accurately detect and classify facial expressions in real-time, allowing for seamless integration into interactive applications and systems. The methodology involves preprocessing facial images to extract relevant features using Haar cascades, followed by providing these features into an ANN architecture for emotion classification. The ANN is trained on a dataset of labeled facial expressions, employing epochs to iteratively refine the model's parameters and enhance its accuracy. Through rigorous experimentation and validation, the system's performance is evaluated, measuring its ability to accurately recognize a diverse range of human emotions in real-time scenarios. The project's significance lies in its potential applications across numerous fields, including human-computer interaction, virtual reality, healthcare, and marketing. Results demonstrate promising accuracy rates, demonstrating the effectiveness of the proposed approach in real-time emotion recognition tasks