Scribd
Upload
7 views10 pages

Fingerprint - Extraction 1 Copy Copy1

Uploaded by

.
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
7 views10 pages

Fingerprint - Extraction 1 Copy Copy1

Uploaded by

.
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 10

A Portable Device for converting Text to

Speech
A MINI PROJECT PRESENTATION

Presentation by: Under Guidance of:

Mandhavadha Sai Vamsi Krishna 21261A0498


Dr Y Praveen Kumar Reddy
Vasala Shiva Kumar 21261A04C7
Diddigi Sai Ram 21261A0484
VII SEM ECE-2 AY2024-25
Aim of the Project
•Enhance Accessibility: Provide a tool that enables visually impaired or
dyslexic individuals to independently access printed text in books, menus,
labels, signs, and other everyday sources.
•Real-Time Text Recognition and Speech Output**: Ensure that the device
can quickly capture text, process it using OCR, and provide immediate
audio feedback, enabling users to interact with their surroundings more
efficiently.
•User Independence: Empower users by reducing their reliance on others
for reading assistance, promoting greater independence in daily activities.

4-ECE-2 Sem-I AY2023-24 2


ABSTRACT
This project aims to create a device using Raspberry Pi that converts
text into audio to assist visually impaired individuals. By combining a
camera, text recognition software (OCR), and text-to-speech (TTS)
technology, the system captures images of text, extracts the written
content, and reads it aloud. The goal is to provide a cost-effective,
portable, and easy-to-use solution that enhances accessibility and
independence, allowing users to read books, signs, documents, and
more without the need for sighted assistance.

23/12/2024 4-ECE-2 Sem-I AY2023-24 3


INTRODUCTION

23/12/2024 4-ECE-2 Sem-I AY2023-24 4


• Develop a low-cost, portable assistive technology system for
visually impaired individuals using the Raspberry Pi.
• Raspberry Pi Serves as the Central Processing Unit
• Real-time audio feedback for immediate user assistance.
• Enhance independence and safety for blind or visually impaired
users.
• Refine the system based on feedback for wider application and
increased accessibility.

23/12/2024 4-ECE-2 Sem-I AY2023-24 5


Steps involved
• Set up hardware: Install Raspberry Pi, camera, microphone, speaker, and power
supply.
• Install software: Set up Raspberry Pi OS, Python, OCR (e.g., Tesseract), and TTS
(e.g., Google TTS).
• Develop code: Write scripts to capture images, process them, extract text, and
convert it to speech.
• Create UI: Develop a simple interface for user interaction, optionally with voice
commands.
• Test: Ensure accuracy with different text types and calibrate as needed.
• Deploy and maintain: Use the system, provide training, and regularly update
software and hardware.

23/12/2024 4-ECE-2 Sem-I AY2023-24 6


Advantages
• Helps Visually impaired people hear written text

• Makes more information available to everyone

• Allows user to carry and use the device wherever you go

• It is easy to use

• Designed to be simple and easy for visually impared individual to use

23/12/2024 4-ECE-2 Sem-I AY2023-24 7


Applications
• Reading Books
• Documents
• Bank Statements
• Mail
• Recipes
• Educational Materials

23/12/2024 4-ECE-2 Sem-I AY2023-24 8


REFERENCES
1. J Smith, A. Brown, and L. White, “Advanced Techniques for Text Extraction and
Translation from Scanned Documents,” International Journal of Document Analysis and
Recognition, 27(4), pp. 789-805, 2024. https://doi.org/10.1007/s10032-024-00567-8

2. L. Chen and S. Kumar, “Deep Learning Approaches for Text Recognition and Translation
in Digitized Historical Manuscripts,” Computer Vision and Image Understanding, 212, pp.
104-118, 2024. https://doi.org/10.1016/j.cviu.2024.103456

3. M. Zhang, H. Wang, and T. Lee, “Improving OCR Accuracy for Historical Documents
Using Deep Learning,” IEEE Transactions on Image Processing, 33(7), pp. 2345-2358,
2024. https://doi.org/10.1109/TIP.2021234567

23/12/2024 4-ECE-2 Sem-I AY2023-24 9


THANK YOU

23/12/2024 4-ECE-2 Sem-I AY2023-24 10

You might also like