Exploring Sign Language Recognition using Convolutional Neural Network

The recognition of sign language holds significant utility in facilitating communication for the hearing-impaired, aiding in robotic interactions, and connecting with non-verbal communities. This field has evolved from early electric signal-based methods to contemporary approaches utilizing machine and machine learning techniques. In this project, the primary objective is to implement sign language recognition (SLR) based on key point detection. The model is trained using a variety of machine learning algorithms, such as random forest, support vector machine, and k-nearest neighbor. The optimal model is determined through testing and evaluation metrics such as f1 score, precision, and recall. Leveraging Media Pipe for hand tracking and key point detection enhances the project's capabilities. The video is captured through a webcam using Open CV, and the model predicts gestures, allowing the robot to respond accordingly based on the recognized sign language gestures.