Sign Language Detection Using Action Recognition LSTM Deep Learning Model

This project aims to develop a system that can recognize sign language gestures in real-time using computer vision techniques. The system is designed to bridge the communication gap between individuals with different hearing abilities by enabling accurate and effective communication through sign language. To achieve this, an image datasets is created, consisting of labeled images of sign language gestures for alphabets, digits, or other signs. This datasets is used to train a deep neural network using transfer learning techniques. Transfer learning involves leveraging the knowledge gained from pre-trained models, such as VGG-16 and ResNet, to accelerate the training process and improve the accuracy of the model. The trained deep neural network is then deployed in a real- time setting where it processes video feeds or live camera feeds to recognize and interpret sign language gestures. The system is designed to be user-friendly, with an intuitive interface that can be easily used by individuals with hearing difficulties or those who do not understand sign language The accuracy of the system is evaluated using various performance metrics such as accuracy, precision, recall, and F1 score. The system is tested in different environments, including noisy and low-light settings, to ensure that it can recognize sign language gestures accurately. Overall, this work demonstrates the potential of computer vision and deep learning techniques to improve communication for individuals with hearing difficulties. It also highlights the importance of developing accessible technologies that can enable effective communication and improve the quality of life for individuals with disabilities