To understand the exact context of the symbolic expressions of deaf and dumb person and provide an efficient and accurate way to convert the sign language into text. ASL (American Sign Language) is used to detect and predict the hand signs of the deaf and dumb person. ASL is a complete, natural language that has the same linguistic properties as spoken languages, with grammar that differs from English. ASL is expressed by movements of the hands and face.
CNN Architecture - Model Building and Training
https://drive.google.com/drive/folders/1AsINuT2OAHplH16Cc8nG4QdjRAK_5erp?usp=sharing
Evaluate the trained model using Accuracy, Precision, Recall, F1 score, confusion matrix. At first, CNN model will be tested with the existing image dataset and then the CNN model s used to predict the real time hand sign images. In the real-time prediction step, hand positions will be captured using a python library and will sent to the model for prediction. Now the trained model finds the best match for the given sign and output the predicted label.