Sign Language Recognition using Deep CNN with Normalised Keyframe Extraction and Prediction using LSTM

Sign Language Recognition (SLR) targets interpreting the signs so as to facilitate communication between hearing or speaking disabled people and normal people. This makes signers effective seamless. The scarcely available key information regarding gestures is recognise signs. To implement continuous sign language gesture recognition, are identified from video using Deep Convolutional Neural Network. Recurrent Network- Long Short-Term Memory verifies semantics of sequence, which eventually will be converted into speech. problem constructing meaningful sentences inspired proposed system develop a model based on it. designed increase effectiveness classification by processing only principal elements. keyframes processed for classification. Validation can done O(N). voiceover have elegant impaired obtained an accuracy 89.24% while training over Network detect performed better than other pre-trained models 89.99% predict next word grammar phrases. keyframe-to-voice conversion, forming proper sentences, enthrals harmonious communication.