This project implements a gesture recognition system using a Convolutional Neural Network (CNN) to classify hand gestures: open palm, fist, and thumbs-up for both left and right hands.
Dataset (File video_frame.ipynb used for dataset extraction from videos) Creation: Videos recorded and frames extracted (1500 images total). Split: 900 images for training, 600 for testing.
Model (File gesture_recognition_system) Architecture: Two convolutional layers, three fully connected layers. Optimizer: SGD with Cross Entropy Loss.
Results Accuracy: 97.01% F1 Score: 0.97