Abstract:
The objective of this project is to propose and develop sign language recognition system with simpler deep learning models. This report explores and compares different deep learning techniques used for the recognition of Pakistan Sign Language. This report also identifies the challenges and limitations of developing such a proposed system with a very limited dataset. This report also compares the results of complex models with the simpler models. Several preprocessing and augmentation and extraction techniques are discussed. This report also explores the diverse Pakistan Sign Language dictionary dataset and reports its limitations. The final deliverable of this report are AI models that can be used in real time to recognise the Pakistan sign language.
