ABSTRACT

Due to eye diseases, age related causes, uncontrolled diabetes, accidents and other
reasons, the number of visually impaired persons are increasing every year. One of the most
significant difficulties for a visually impaired person is to read. Speech and text is the main
medium for human communication. A person needs vision to access the information in a text.
However, those who have poor vision can gather information from voice. Recent
developments in mobile phones, computers, and availability of digital cameras make it
feasible to assist the blind person by developing camera based applications that combine
computer vision tools with other existing beneficial products such as Optical Character
Recognition (OCR) system.

The proposed system is a camera based assistive text reading aid which helps visually
impaired person in reading the text present on the captured image. The faces can also be
detected when a person enter into the frame by the mode control. The proposed idea involves
text extraction from scanned image using Tesseract Optical Character Recognition (OCR)
and converting the text to speech by e-Speak tool, a process which makes visually impaired
persons to read the text. This is a prototype for blind people to recognize the products in real
world by extracting the text on image and converting it into speech. Proposed method is
carried out by using Raspberry pi and portability is achieved by using a battery backup. This
technology helps millions of people in the world who experience a significant loss of vision.
This project is economical, portable and implemented with open source hardware and
software to assist the visually impaired person.

i
 ACKNOWLEDGEMENT
The project of any research work depends so much on: the quality of education
received the quality of teachers, research resources and enabling and encouraging
environment. Studying in Alva’s Institute of Engineering and Technology, Mijar provides
all these above mentioned facilities which have made possible the successful outcome of this
research work.

Firstly, our gratitude goes to our guide, Mr. Sahana K Adyanthaya., Assistant
Professor, Department of Electronics and Communication, AIET, who is our source of
encouragement and motivation throughout this project. Without his valuable guidance, this
work would never have been a successful one.

We would like to express our heartily gratitude to our Project coordinator,

Mr. Shankar B B., Assistant Professor, Department of Electronics and Communication,
AIET, for his consistent guidance, regular source of encouragement and assistance
throughout this project

We would like to express our sincere gratitude to our Head of the Department of
Electronics & Communication Engineering, Dr. D V Manjunatha for his guidance and
inspiration.

We would like to thank our Principal Dr. Peter Fernandes for providing all the
facilities and a proper environment to work in the college campus.

We are indebted to Management of Alva’s Education Foundation, Moodbidri for

providing an environment which helped us in completing our project.

We are thankful to all the teaching and non-teaching staff members of Department of
Electronics & Communication Engineering for their help and needed support rendered
throughout the project.

ii
 TABLE OF CONTENTS
TITLE Page No.

ABSTRACT i
ACKNOWLEDGEMENT ii

TABLE OF CONTENTS iii

LIST OF FIGURES v
LIST OF TABLES viii
LIST OF ABBREVIATIONS ix

CHAPTER 1: INTRODUCTION 1
1.1 Prelude 1
1.2 Aim of the project 1
1.3 Existing system 1
1.4 Proposed system 2
1.5 Objective of the proposed system 2
1.6 Motivation 2
1.7 Organization of the report 3
CHAPTER 2: LITERATURE SURVEY 4
2.1 Introduction 4
2.2 Literature review 4
CHAPTER 3: FUNDAMENTALS OF THE PROJECT 16
3.1 Hardware Components 16
3.2 Software Tools 16
3.3 Block Diagram of the Proposed System 17
3.4 Raspberry pi 17
3.4.1 Hardware 19
3.4.2 Processor 19
3.4.3 Performance 21
3.4.4 Overclocking 21
3.4.5 RAM 23
3.4.6 Software Operating Systems 23
3.4.7 Python Installation on Window 27
iii
 3.4.8 Installation of PuTTY software on Windows 35
3.4.9 Installation of VNC Server in Windows 37
3.4.10 Other Operating Systems (not Unix/Linux-based) 42
3.4.11 Other Operating Systems (Unix/Linux-based) 42
3.5 Pin diagram of Raspberry Pi 45
3.5.1 GPIO Numbering 46
3.5.2 Physical Numbering 46
3.6 Features of Raspberry Pi 46
3.6.1 Advantages of Raspberry Pi 47
3.6.2 Disadvantage of Raspberry Pi 47
3.7 Tesseract OCR 48
3.7.1 Features 48
3.8 E-speak tool 49
3.8.1 Features 49
3.9 Digital Image Processing 49
CHAPTER 4: METHODOLOGY 51
4.1 Architecture of the Proposed System 51
4.2 Flow Chart of the Proposed System 52
CHAPTER 5: IMPLEMENTATION OF THE SYSTEM
5.1 Introduction 54
5.2 Working of Proposed System 54
5.2.1 Camera
54
5.2.2 Mode Selection
5.2.3 Face Detection 55
5.2.4 Text Detection
55
5.2.5 Noise Correction and Sound Indication
5.2.6 Thresholding 55
5.2.7 Tesseract OCR
56
5.2.8 E-speak Tool
5.2.9 Audio Output 56
5.2.10 Conversion of Text to Voice using E-speak Tool
57
5.2.11 Software Implementation
57
58
58
59

iv
CHAPTER 6: RESULTS AND DISCUSSIONS 75

CHAPTER 7: CONCLUSION AND FUTURE WORK 76

7.1 Conclusion 77
7.2 Future scope 78
REFERENCES 79

APPENDIX

LIST OF FIGURES

v
Fig. No. DESCRIPTION OF THE FIGURES Page No.

Figure 3.1 Block diagram of the proposed system 17

Figure 3.2 Raspberry Pi board 17
Figure 3.3 Different version of python 28
Figure 3.4 Required version of python 29
Figure 3.5 Selecting install for all user 29
Figure 3.6 Selecting destination directory 30
Figure 3.7 Selecting add python.exe to path 30
Figure 3.8 Python installation window 31
Figure 3.9 Python installation setup was successful 32
Figure 3.10 Python system properties 33
Figure 3.11 Python environment variable 34
Figure 3.12 Selecting python3.exe and python.exe 35
Figure 3.13 Python working window 35
Figure 3.14 Putty configuration 36
Figure 3.15 Putty security alert 37
Figure 3.16 Selecting run 38
Figure 3.17 Selecting the language 38
Figure 3.18 VNC setup wizard 38
Figure 3.19 VNC operation 39
Figure 3.20 Custom setup 39
Figure 3.21 Ready to exchange VNC viewer 40
Figure 3.22 VNC server status 40
Figure 3.23 VNC setup wizard ended prematurely 41
Figure 3.24 Raspberry Pi component 45
Figure 3.25 Pin diagram of raspberry Pi 45
Figure 4.1 System architecture 51
Figure 4.2 Flow chart of the proposed system 52
Figure 5.1 Selecting putty software 59

vi
Figure 5.2 Typing the IP address 59
Figure 5.3 Putty login ID 60
Figure 5.4 Password window 60
Figure 5.5 Ls command window 61
Figure 5.6 VNC server path 61
Figure 5.7 Selecting VNC software 62
Figure 5.8 VNC viewer window 62
Figure 5.9 Encryption window 63
Figure 5.10 Authentication window 63
Figure 5.11 Raspberry Pi desktop 64
Figure 5.12 Raspberry Pi project window 65
Figure 5.13 Text recognition python code 66
Figure 5.14 Executing text recognition code 67
Figure 5.15 Face detection code 68
Figure 5.16 Face detection code 69
Figure 5.17 Executing face detection code 70
Figure 5.18 Executing face detection code 71
Figure 5.19 Detected face set1 72
Figure 5.20 Detected face set2 73
Figure 5.21 Shutdown command 73
Figure 6.1 System design 75

vii
 LIST OF TABLES

Table No. DESCRIPTION OF THE TABLES Page No.

Table 3.1 Python environment variable 26

viii
 LIST OF ABBREVATIONS

ADC Analog to Digital Converter

AIC Alkaike Information Criterion

ANSII American National Standard Institute

BCM Broadcom

BOVW Bag of Visual Words

CPU Central Processing Unit

CRF Conditional Random Field

CV Computer Vision

DMP Deformable Models Parts

DOS Disc Operating System

FDR Fisher’s Discriminant Rate

GMM Gaussian Mixture Model

GMW Globally Matched Wavelet

GPIO General Purpose Input/Output

GPS Global Positioning System

GPU Graphics processing unit

GSM Global System for Mobile Communication

HDMI High Definition Multimedia Interface

HOG Histogram of Oriented Gradients

HTML Hyper Text Markup Language

ICA Independent Component Analysis

IoT Internet of Things

IP Internet Protocol

LAN Local Area Network

ix
LFW Labeled Faces in the Wild

LVCSR Large Vocabulary Continuous Speech Recognition

MATLAB MATrix LABoratory

OCR Optical Character Recognition

OOP Object Oriented Programming

OTG On The Go

OTSU Operational Test Support Unit

OS Operating System

PCA Principal Component Analysis

PDA Personal Digital Assistant

PERL Practical Extraction and Report Language

PoE Power over Ethernet

RFB Remote Frame Buffer

RFID Radio Frequency Identification

RISC Reduced Instruction Set Computer

ROI Region of Interest

RTC Real Time Clock

SAPI Speech Application Programing Interface

SD Secured Digital

SDRAM Synchronous Dynamic Random Access Memory

SIFT Scale Invariant Feature Transform

SL Spatial Language

SOC System on a Chip

SSH Secure Shell

SSML Speech Synthesis Markup Language

SURF Speeded UP Robust Feature

x
SVM Support Vector Machine

TTS Text to Speech

USB Universal Serial Bus

VNC Virtual Network Computing

WI-FI Wireless Fidelity

WWW World Wide Window

xi