Sign Language Recognition using Deep Learning

The goal of this deep learning project is to create a model for sign language recognition using a convolutional neural network (CNN), utilising the Keras package and OpenCV for live picture capture. This Sign Language Recognition (SLR) model follows a vision-based approach, where the features corresponding to the palms, finger position and joint angles are estimated and are then used to perform recognition. This method requires acquiring images of the signs through a camera and processing using image processing techniques. To build the sign language recognition model, MNIST ( Modified National Institute of Standards and Technology) dataset. This dataset consists images of alphabets and numbers, each image having a size of 28x28 pixels which gives a total of 784 pixels per image.