IRJET - Hand Gesture Recognition to Perform System Operations

This document describes a hand gesture recognition system that uses deep learning and convolutional neural networks. The system is trained on a dataset of over 50,000 images to recognize 19 different gestures. It first calibrates the background, segments the hand from the image, and recognizes the gesture. The model achieves 86.39% accuracy on the test set after training for 20 epochs with a batch size of 64 using an Adam optimizer.