IRJET-Raspberry Pi based Reader for Blind People
0 likes106 views
This document describes a Raspberry Pi-based reader device for blind people that uses optical character recognition (OCR) and text-to-speech to allow visually impaired users to access printed text. The system uses a webcam to capture an image of text, the OCR software converts the image to text, and a text-to-speech engine converts the text to audio that is output through speakers. The document provides details on the components, workflow, and implementation of the system to help blind individuals access and understand printed documents independently.
![International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 06 Issue: 04 | Apr 2019 www.irjet.net p-ISSN: 2395-0072
© 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 3041
3.3 OCR Software Design
Fig- Voice Processing Module using text to speech system
Text is converted into voice by using text to speech system.
The output of OCR is text which is stored in file
(file.txt).Festival is the open source software is used for
conversion of text to speech. Text is read by English TTS
system
4. Design Implementation
1. Raspberry pi 3(model B+)
2. Web camera
3. Headset
4. Power supply
5. Peripherals (Mouse, Keyboard, Camera)
5. Flow of Program
Fig: Flow chart for text to speech converter
6. Result
Text is extracted from image as a input and
converted into audio as a output.
It extract capital as well as small letters.
Range of reading distance from 12-14cm.
7. Conclusion
Text to speech coverter device convert the text input image
into audio output. Average processing time required is less
than 2 minutes. This device does not require internet
connection and can be use independently by people.
Reference
[1] K. Nirmala Kumari, Meghana Reddy Image, “Text to
Speech Conversion Using OCR Technique in
Raspberry Pi” Vol. 5, Issue 5, May 2016
[2] Asha G. Hagargund, Sharsha Vanria Thota, Mitadru
Bera, Eram Fatima Shaik “Image to speech
conversion for visually impaired”,Volume 03 - Issue
06 June 2017
[3] Nagaraja L, Nagarjun R S, NishanthMAnand“Vision
based Text Recognition using Raspberry Pi” 2015
[4] A. Subbiah*, T. Arivukkarau, M. S. Saravanan, V.
Balaji “camera based label reader for blind
people”,2016, 840-844 ISSN 0972-768X
[5] Mrs.Shilpa Reddy K, Mounika S.K,PoojaK,SahanaN
“Text to Speech fortheVisuallyImpaired”,Volume4
, May 2017
[6] Sanjana.B, J. Rejina Parvin “Voice assisted text
reading system for visually impaired persons using
TTS method”) volume 6, issue 3, May 2016](https://image.slidesharecdn.com/irjet-v6i4651-190708050955/85/IRJET-Raspberry-Pi-based-Reader-for-Blind-People-2-320.jpg)
IRJET-Raspberry Pi based Reader for Blind People
- 1. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 06 Issue: 04 | Apr 2019 www.irjet.net p-ISSN: 2395-0072 © 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 3040 Raspberry Pi Based Reader for Blind People Ashanta waghmare1, Bhagyashri Sawale2, Mohini Pangare3, Urmila Shinde 4, Ashish Jadhav5 1,2,3,4Student. Dept. of SVERI’s College of Engineering, Pandharpur, Maharashtra, India 5Professor. Dept. of SVERI’s College of Engineering, Pandharpur, Maharashtra, India ---------------------------------------------------------------------***---------------------------------------------------------------------- Abstract – Text and Speech is the main resources of communication. Vision is required to accesstheinformationin a text. Visually impaired people face lots of difficulties while accessing printed documents. Access various text resources and enhance their knowledge by providing technical solution is the main scope of this project. In this Proposed System we use WEB Camera for capturing the image. This captured image is then converted into text with the help of OCR (Optical Character Recognition) software. TTS (Text to Speech)engine is used to convert text to speech. . Key Words: Raspberry Pi, WEB Camera, Optical Character Recognition (OCR), Text To Speech (TTS) Engine 1. INTRODUCTION While accessing printed text by using existing technology visually impaired people face numerous difficulties regarding to the alignment, focus, accuracy, mobility and efficiency. This paper proposes the smart reader for visually impaired people. To read text document camera based assistive methodology is used as a input. Captured image by web camera is converted into machine coded text by using OCR(Optical Character Recognition).The audio output is achieved by using text to speech synthesis through speaker. Tesseract library and python programming is used for conversion of printed documents into text file by using Raspberry pi. 2. Block Diagram Fig: Block diagram of raspberry pi based reader for blind 3. Methods Image processingandvoice processingarethemainmodules in text to speech device. Image into text is converted by image processing module and text into sound conversion is done by voice processing module. Fig: Block Diagram of Text to speech device Fig shows the block diagram of text to speech conversion device. The first module converts .jpg to .txt form. Second module converts the .txt into speech. 3.1 Image Processing Module In this module OCR is the main element. This technology recognize the character through optical mechanism. This technology has the ability of express the human senses of sight, where the replacement of eye is camera and the substitute for human brain is computer engine in which image processing is done. Flexibilty and extensibility of machine is the main reason for selection of tesseract engine. Image is converted into binary form before feeding to the OCR to increase the recognition accuracy. Imagemagick software is used for image binary conversion which is open source tool for image manipulation. The output of OCRisthe text which is stored in file. 3.2 OCR Implementation Webcamera captures the input image. Pixel is the minimum character size which can be read by tesseract OCR and the font size required is 14pt.
- 2. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 06 Issue: 04 | Apr 2019 www.irjet.net p-ISSN: 2395-0072 © 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 3041 3.3 OCR Software Design Fig- Voice Processing Module using text to speech system Text is converted into voice by using text to speech system. The output of OCR is text which is stored in file (file.txt).Festival is the open source software is used for conversion of text to speech. Text is read by English TTS system 4. Design Implementation 1. Raspberry pi 3(model B+) 2. Web camera 3. Headset 4. Power supply 5. Peripherals (Mouse, Keyboard, Camera) 5. Flow of Program Fig: Flow chart for text to speech converter 6. Result Text is extracted from image as a input and converted into audio as a output. It extract capital as well as small letters. Range of reading distance from 12-14cm. 7. Conclusion Text to speech coverter device convert the text input image into audio output. Average processing time required is less than 2 minutes. This device does not require internet connection and can be use independently by people. Reference [1] K. Nirmala Kumari, Meghana Reddy Image, “Text to Speech Conversion Using OCR Technique in Raspberry Pi” Vol. 5, Issue 5, May 2016 [2] Asha G. Hagargund, Sharsha Vanria Thota, Mitadru Bera, Eram Fatima Shaik “Image to speech conversion for visually impaired”,Volume 03 - Issue 06 June 2017 [3] Nagaraja L, Nagarjun R S, NishanthMAnand“Vision based Text Recognition using Raspberry Pi” 2015 [4] A. Subbiah*, T. Arivukkarau, M. S. Saravanan, V. Balaji “camera based label reader for blind people”,2016, 840-844 ISSN 0972-768X [5] Mrs.Shilpa Reddy K, Mounika S.K,PoojaK,SahanaN “Text to Speech fortheVisuallyImpaired”,Volume4 , May 2017 [6] Sanjana.B, J. Rejina Parvin “Voice assisted text reading system for visually impaired persons using TTS method”) volume 6, issue 3, May 2016