Sign Language Detection using LSTM

Sign language is used by speech and hearing-impaired people as a method of communication. There are thousands of sign languages used all around the globe. Understanding sign language is a challenging task for a normal person. At present, speech and hearing-impaired people depend on human translators to make this task easier, but it is not always feasible to have a human translator. The objective of the present work is to design and implement an algorithm which detects real-time sign language using deep learning. The proposed system uses a Long Short-term memory model to train the dataset. The LSTM model works similarly as compared to recurrent neural networks. LSTM neural networks are used for the classification of sign language actions. A deep learning neural network is similar to the human brain in that it uses a combination of factors such as inputs, weights, and biases to perform various tasks, such as identifying and classifying objects. Deep learning algorithms work better when they are trained with a large amount of data. The performance of the proposed system has been evaluated based on accuracy, precision, and recall. The dataset consists of a Marathi sign which are daily used. The output of sign gesture is in text as well as in audio format. For audio we used google text to speech library. The proposed system could classify seven gestures with the highest training accuracy of 90-96%.