In worldwide there are 314 million visually impaired people and blind, out of which 45 million are visual impairment which was released by “World Health Organization” in 10 facts regarding blindness. Reading is obviously necessary in today’s society. Printed text appears everywhere in the form of receipts, bank statements, reports, restaurant menus, classroom notes, product labels, instructions on medicine bottles, etc The blind people cannot read the text on printed papers and they cannot recognize objects. Therefore, we are developing this project which help to the blind people in doing the above-mentioned tasks. The project aims at designing a raspberry pi and pi camera-based text to speech conversion and object recognition. with voice announcements. The portable system which captures the text written on printed papers which is placed in front of the pi camera. And process this text to the raspberry pi. Raspberry pi will convert this text into speech and gives the voice through speaker. In this project we are using Python-tesseract is an optical character recognition (OCR) tool for python. OpenCV image processing for object recognition. This is a simple python project that extracts the text from the image. Store the text into a text file. Then retrieves that text from the file and convert it into a speech.      

Objectives:

• Text to speech conversion and Object recognition for blind persons.

       

The major building blocks of the project are:

1. Power supply.
2. Raspberry Pi3 b+ processor.
3. Pi Camera.
4. SD card.
5. Speaker.

         

Software’s used:

1. Raspbian OS.
2. Embedded Linux programming.
3. Express SCH for Circuit design.
4. Python-tesseract is an optical character recognition (OCR).
5. Espeak to read the English text.
6. OpenCV image processing for object recognition.

           

         

video: