Raspberry Pi Based Reader for Blind People

The project uses the methodology of a camera based assistive device that can be used by people to read Text document. The framework is on implementing the image capturing technique in an embedded system based on Raspberry Pi board. The design is motivated by preliminary studies with visual

Project Title

Raspberry Pi Based Reader for Blind People

Project Area of Specialization

Artificial Intelligence

Project Summary

The project uses the methodology of a camera based assistive device that can be used by people to read Text document. The framework is on implementing the image capturing technique in an embedded system based on Raspberry Pi board. The design is motivated by preliminary studies with visually impaired people. 

In this project, we aim to make a device which will provide reading assistance to blind people in real time by converting the printed or typed text into voice. Raspberry Pi is the brain of this device which is connected with a camera which will capture the image containing text and optical character recognition (OCR) is used for the detection of text and computer programming for the conversion into voice signals. Python programming along with Tesseract library and Espeak open source software is used for the purpose of processing image capturing & detection, conversion into digital signals

Project Objectives

he main objectives of this project is to design a blind reader device which will have the following features,

• Read & Convert the text into a voice form in real time
• Read the text of any type of font and Convert it into Voice Form
• Read the text of any font size in Voice Form
• Capable of Lowering or increasing the speed of voice output
• Capable of having different type of voices

Project Implementation Method

The proposed project will be done in five phases as follows:

Phase 1

• Comprehensive study of the major concepts involved in Image processing using OCR and its Conversion into Voice signals. 
• Gathering information regarding the utilization of raspberry Pi for the implementation image processing and text to speech conversion,

Phase 2:

• Performing the cost benefit analysis to design a system using camera, Raspberry Pi and Speakers for Image processing and text to speech.
• Checking the feasibility of Softwares like MATLAB & Python.

Phase 3:

• Testing software with the speed precision & quality of voice signals which are the output of the project.

Phase 4:

• Implementing the code with Hardware on raspberry Pi.
• Applying the image processing and text to speech modules on hardware.

Phase 5:

• Testing the designed system with number of texts in real-time and improving the voice quality.
• Documentation 

Benefits of the Project

As there are large number of visually people in Pakistan and visually impaired people report numerous difficulties with accessing printed text using existing technology, including problems with alignment, focus, accuracy, mobility and efficiency. The project will provide the solution. A Majority of the visually impaired use Braille for reading documents and books which are difficult to make and less readily available. Hence this device will help the blind people to read the printed text and through this device issues of large proportion of society will be addressed which are disabled. The project will have massive applications in Pakistan and will be solving a major issue of less privileged part of society that are Visually Impaired people.

The scalability of this project can be seen that its major component are Raspberry Pi, a camera, & python as interface and programming language. All these three things are easily available in all parts of world. Secondly the language we are working on is English. Out of the world's approximately 7.5 billion inhabitants, 1.5 billion speak English that's 20% of the Earth's population. So the project can be adapted in majority of regions and communities of the world.

The projects can lead to assistive ring for blind people which will have millions of application round the world.

The proposed method can furthur be extended for object detection, currency detection, for other languages too. 

Technical Details of Final Deliverable

• Hardware of the complete image processing and text to speech module which includes Camera, Speaker and Raspberry Pi.
• Software of Image processing
• Software of Text to Speech
• Graphical User Interface for Client Side
• Project Report

Final Deliverable of the Project

Hardware System

Type of Industry

Medical

Technologies

Artificial Intelligence(AI)

Sustainable Development Goals

Good Health and Well-Being for People, Industry, Innovation and Infrastructure

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com