Objective ​This project uses Convolutional Neural Networks (CNNs) to detect and classify human facial emotions from static images and real-time webcam input. The system identifies seven fundamental emotions: Happiness, Sadness, Anger, Surprise, Fear, Disgust, and Neutral.
​ Technical Summary ​Frameworks: TensorFlow, Keras, and OpenCV.
​Dataset: FER-2013 containing ~35,000 grayscale facial images.
​Model: Sequential CNN with multiple convolutional layers, batch normalization, and dropout.
​Performance: Final test accuracy of 64.7%.