Around 314 million people worldwide are visually impaired, including about 45 million who are blind. Reading printed text such as books, bills, labels, and documents is difficult for them. This project develops a Raspberry Pi 3-based text reader using a Pi Camera to capture printed text. The captured image is processed using Python Tesseract OCR to extract the text, which is then converted into speech and played through headphones, enabling visually impaired users to access printed information independently.    

Objectives of the Project:

• To capture printed text using a Raspberry Pi Camera.
• To extract text from images using OCR (Python Tesseract).
• To convert the extracted text into speech for audio output.
• To assist visually impaired people in reading printed documents independently.
• To develop a portable and easy-to-use text reading system using Raspberry Pi.

    The main blocks of this project are:

• 7V battery Power Supply.
• Raspberry Pi processor.
• Pi Camera.
• Headphones.
• Switch.

      Software’s used:

1. Raspbian OS.
2. Embedded Linux programming.
3. Express SCH for Circuit design.

         

video: