Technical College of Engineering-Mosul, Northern Technical University discussed a master dissertation on designing and implementing of smart reader glasses for the blind.
The dissertation by the postgraduate student, Ms. Hoda Salim Jassim aims at creating a system that helps individuals with visual disabilities read documents in various fields written in Arabic and English and converting them into audio audible to the blind person via headphones.
The dissertation reviewed using of a deep learning model to recognize the contents of a document, as well as recognizing text and convert it into text strings in String format via text-to-speech technology using Google Text-to-Speech (gTTS) technology, as well as implementing the SRG system using three deep learning models ( YOLOv5s and YOLOv5m).
The dissertation recommended adding a higher-resolution camera to improve image quality, improving optical character recognition and using a larger, more diverse data set to improve the system, as well as expanding the scope of the search to include different types of documents, including old archival documents that often contain large amounts of noise.
