Machine Learning based Hand Gesture Recognition System for Assistive Communication for People with Adaptive Needs

This proposed system uses machine learning techniques to improve communication for individuals with mobility challenges, such as those who are deaf or hard of hearing, by interpreting hand gestures. Current technologies that convert sign language into speech are often complex and lack accuracy. This proposes using machine learning algorithms to enhance the recognition and interpretation of hand gestures. The system leverages deep learning techniques, particularly Convolutional Neural Networks (CNNs), to achieve high accuracy in gesture recognition. Through the application of deep learning models trained on large datasets of hand gesture movements, this system will accurately translate specific gestures into commands for control and communication. In this work, the gestures are analyzed to deliver the corresponding output, and the word formation is enhanced to facilitate an easier understanding of the gestures. Additionally, the gesture analysis includes suggesting words to help form complete sentences. This approach aims to improve both the accuracy and efficiency of gesture-based interactions.