Sign language recognition and detection (SLR) systems are designed in order to interpret and translate sign language gestures into textual or speech form, allowing for improved communication for hard-hearing individuals. The main objective of SLR systems is to provide a feasible and an efficient medium of communication between normal and deaf people by using hand gestures. Webcam or an in-built camera is used in these systems which detects and processes the sign language captured by the camera and the model deployed recognizes it. Recent advances in machine learning and deep learning techniques have greatly improved the accuracy of SLR systems. However, the technology still faces challenges such as environmental factors and limited training data. This paper provides an overview of the current state of SLR systems and analyzes the performance of existing ML technologies in sign language recognition tasks.

CNN, deaf/dumb, GRU, LSTM, OpenCV, Mediapipe, Sign language Recognition