International Journal of Trend in Scientific Research and Development (IJTSRD)

Volume 5 Issue 3, March-April 2021 Available Online: www.ijtsrd.com e-ISSN: 2456 – 6470

Recognizing of Text and Product Label from Hand

Held Entity Intended for Visionless Persons
Arunkumar. V1, Aswin M. D1, Bhavan. S1, Gopinath. V1, Dr. Kishorekumar. A2
1UG
Scholar-ECE, 2Associate Professor-ECE,
1,2Hindusthan College of Engineering and Technology, Coimbatore, Tamil Nadu, India

ABSTRACT How to cite this paper: Arunkumar. V |

Our proposed work involves recognizing text and product label reading from Aswin M. D | Bhavan. S | Gopinath. V | Dr.
portable entities intended for Visionless Persons using Raspberry Pi 3, Kishorekumar. A "Recognizing of Text and
ultrasonic sensor. Raspberry Pi 3 is the controller used in the proposed device. Product Label from Hand Held Entity
GPS is fixed in the system and it is used to find the exact location of the person Intended for Visionless Persons"
in terms of longitude and latitude, this information is sent to the caretaker Published in
through e-mail. The caretaker can use the latitude and longitude to find the International Journal
address on Google Maps. The camera is used to identify the obstacle or object of Trend in Scientific
ahead and the output is told to the blind user in speech form. The camera also Research and
identifies objects with words on them, using image processing these images Development (ijtsrd),
are converted to text, and using Tesseract the text is converted to speech, thus ISSN: 2456-6470,
giving the speech output to the blind about what is written on the object. RF- Volume-5 | Issue-3, IJTSRD39808
ID is used to find the stick using tags. The buzzer goes ON to identify the April 2021, pp.328-
location of the stick. A threshold value for distance between the user and the 330, URL:
stick is set, when the distance is less than the threshold value, the buzzer www.ijtsrd.com/papers/ijtsrd39808.pdf
sound increases.
Copyright © 2021 by author(s) and
KEYWORDS: Recogonization of text and object for blind people International Journal of Trend in Scientific
Research and Development Journal. This
is an Open Access article distributed
under the terms of
the Creative
Commons Attribution
License (CC BY 4.0)
(http://creativecommons.org/licenses/by/4.0)

1. INTRODUCTION 2. LITERATURE SURVEY

Reading is important for today’s society. Text is all over A literature survey is that the study of already established
within the sort of printing reports, receipts, bank statements, systems associated an assortment of knowledge that helps in
eating house menus, product packages, directions on drugs doing new tasks. In [1], study on speech synthesis
bottles, and so forth And whereas optical aids, video technology using image recognition technology (Optical
magnifiers, and screen readers will facilitate blind persons Character Recognition) to develop a cost effective user
and people with less vision to access documents, few devices friendly image to speech conversion system using MATLAB
can offer higher access to common hand-held objects for blind person was discussed.
equivalent to product packages and objects written with text
In [2], authors formulated the interaction between image
such as prescription This paper presents a paradigm system
segmentation and object recognition in the framework of
of helpful text reading. There are 3 main components
canny algorithm and the proposed system goes through
enclosed scene capture, information processing, and audio
various phases such as preprocessing, feature extraction,
output. The scene capture part collects scenes containing
object recognition, edge detection, image segmentation and
objects of interest within the sort of images or video. The
text-to-speech (TTS) conversion. In [3], review paper focused
data processing component is used object-of-interest
on well-known methods for better understanding Text
detection and text localization to obtain image regions
recognition in images.
containing text, and text recognition. The recognized text
codes are informed by the audio output component to the In [4], interaction between image segmentation (using
blind user. A Bluetooth earpiece with a mini microphone is different edge detection methods) and object recognition are
employed for speech output. The main contributions of this discussed.
paper are a novel motion-based algorithm is used to solve
In [5], the proposed is system provides indoor navigation by
the aiming problem for blind users by simply shaking the
using Radio Frequency Identifier (RFID), outdoor navigation
object of interest for a brief a novel algorithm of automatic
by using Global Position System (GPS) as well as obstacle
text localization to obtain text regions from the complex
detection by using ultrasonic sensor.
background and multiple text patterns. A portable camera-
based assistive framework to aid blind persons in reading In [6], reviewing the approaches on Text extraction in video
text from hand-held objects. documents, as an important research field of content-based
information indexing and retrieval, is proposed.

@ IJTSRD | Unique Paper ID – IJTSRD39808 | Volume – 5 | Issue – 3 | March-April 2021 Page 328
 International Journal of Trend in Scientific Research and Development (IJTSRD) @ www.ijtsrd.com eISSN: 2456-6470
In [7], this paper proposed a portable camera-based assistive thereto, and ultrasonic waves are transmitted from the
text reading framework to help blind persons to read text ultrasonic probe into the topic to get received signals
labels and product packaging from hand-held objects in their through receiving the ultrasonic waves mirrored among the
daily lives. The system framework consists of three subject, thereby displaying for a designation a carrying info
functional components: First, scene capture-using a mini supported the received signals, associated is additionally
camera, the text which the user needs to read gets captured provided an inaudible module as well as a process circuit for
as an image and has to be sent to the image or data the received signals, the ultrasonic module being employed
processing platform., second, data processing -where text within the ultrasonic diagnostic system.
will be filtered from the surrounding and will be recognized
by optical character recognition (OCR) software, and finally,
Speech output - A filtered text will be passed into this system
to get an audio output.
In [8], an innovative, efficient and real-time cost beneficial
technique that enables user to hear the contents of text
images instead of reading through them as been introduced.
Also described the design, implementation and experimental
results of the device. This device consists of two modules,
image processing module and voice processing module. The
device was developed based on Raspberry Pi v2 with 900
MHz processor speed.
In [9],proposed the novel implementation of smart book
reader with raspberry pi controller. The proposed system is Fig 2 Ultrasonic sensor
under validated with both simulation and experimental
RFId
verification it achieves the text document is converted with
RFID is additionally a rate Identification.
speech for the use of visually impaired people.
An ADC (Automated information assortment technology
3. SYSTEM COMPONENTS DESCRIPTION
that: uses radiofrequency waves to transfer data between a
The Portable camera-based assistive text and product label
reader and a movable item to identify, reason track.Is quick
reading from a handheld object for blind people These
and doesn't need physical sight or contact between the
hardware components are discussed below:
reader/scanner and therefore the labelled item. Operates
Raspberry pi victimization low-priced components. tries to produce
The Raspberry PI may be a tiny single-board pc developed distinctive identification and backend integration that
within the Kingdom, it's small in size, low cost, and it works enables for a large vary of applications.
type of a standard laptop at an inexpensive server to handle
Other ADC technologies: Bar codes, OCR.
web traffic. There are try of} models Raspberry Pi a pair of
and Raspberry Pi 3 4. BLOCK DIAGRAM
The below diagram being represets the block diagram of the
Advantages are as below A
project

Fig 1 Raspberry pi
1.2GHz 64-bit quad-core ARMv8 component 802.11n
Wireless electronic network Bluetooth four.1 Bluetooth Low
Fig 3 Block Diagram of the Proposed system
Energy (BLE) four USB ports forty GPIO pins Full HDMI port
native space network port Combined 3.5mm audio jack and 5. CIRCUIT DESIGN
composite video Camera interface (CSI) show Interface (DSI) The hardware components are connected and then the
little Mount Rushmore State card slot Video Core IV 3D circuit had been designed. The input devices are Ultrasonic
graphics core sensor, Vibration sensor, and camera are connected to the
Raspberry pi and the output devices are Amplifier, Buzzer,
Ultrasonic Sensor
and the audio output. The below diagram represents the
There is provided associate inaudible diagnostic system
circuit design
within which an ultrasonic probe is detachably connected

@ IJTSRD | Unique Paper ID – IJTSRD39808 | Volume – 5 | Issue – 3 | March-April 2021 Page 329
 International Journal of Trend in Scientific Research and Development (IJTSRD) @ www.ijtsrd.com eISSN: 2456-6470

Fig 7 Representative model

7. RESULT & OUTPUT
Image camera captured the photo of Raspberry PI 3 in Pi
Fig 4.Circuit Design Model camera, that feeds to the Raspberry PI model, OCR converts
6. OPTICAL CHARACTER RECOGNITION the image file into the machine code that recognizes by the
Text recognition is performed by off-the-peg OCR before computer and converted it into the text with the use of GTTS
outputting informative words from the localized text (Google text to speech converter) the text data is converted
regions. A text region labels the minimum rectangular space into the speech and output audio is audible by Bluetooth or
for the accommodation of characters within it, that the speaker connected to it.
border of the text region contacts the sting boundary of the 8. CONCLUSION
text However, OCR generates higher performance if text The planned system is supposed to help blind persons to
regions are initial allotted correct margin areas and scan the text label from hand-held objects in their daily life.
binarized to section text characters from the background. we thus therein believe living got to enhance and increase the
tend to propose to use the guide matching algorithmic social growth. The system captures the image of any hand-
program for OCR. The output of the OCR is nothing however held object placed near the camera of Raspberry PI and with
a document containing the merchandise label (its name) in the use of OCR, GTTS final audio output are getting to be
matter form. The audio output part is to tell the blind user of hearable to the blind persons.
recognizing text code within the style of speech or Audio.
9. REFERENCES
[1] Yamini D. Patil, Nandkishore C. Patil, "Optical
Character Recognition Based Text to Speech
Synthesis", JEITR vol.2, Issue 7, July 2018.
[2] MurnanePatil and Ramesh Kagalkar, "A Review on
Conversion of Image to Text as well as Speech using
Edge detection and Image Segmentation", IJSR vol.3,
Issue 11, November 2017.
[3] Pratik MadhukarManwatkar and Dr. Kavita R. Singh
"Text Recognition from Images: A Review" IJARCSSE,
vol.4, no.11, November 2015.
[4] Y. Ramadevi, T. Sridevi, B. Poornima, B. Kalyani
"Segmentation and Object Recognition Using Edge
Fig 5 Connectivity image Detection Techniques” vol.2, no.6, December 2017.
[5] Rupa N.Digole, Prof. S. M. Kulkarni, "Smart Navigation
System for visually Impaired Person", IJARCCE, vol.4,
no.7, July 2016.
[6] J. Zhang, R. Kasturi,” Extraction of Text objects in
Video documents: Recent progress”, Proc. IAP
Workshop Document Anal. Syst., pp. 5-17, 2008.
[7] Sonal I Shirke, Swati Patil, ‘Portable Camera Based
Text Reading of Object for Blind persons ‘Internal
Research Journal of Engineering and Technology
(IRJET), Volume: 13-2018.
[8] K Nirmala Kumari, Meghana Reddy J [2016]. Image
Text to Speech Conversion Using OCR Technique in
Raspberry Pi. International Journal of Advanced
Research in Electrical, Electronics and
Instrumentation Engineering Vol. 5, Issue 5, May
2016.
[9] D. Velmurugan, M. S. Sonam, S. Umamaheswari, S.
Fig 6 Connectivity images
Parthasarathy, K. R. Arun [2016]. A Smart Reader for
HOW IT WORKS: The below picture represents the working Visually Impaired People Using Raspberry PI.
Model. International Journal of Engineering Science and
Computing IJESC Volume 6 Issue No. 3.

@ IJTSRD | Unique Paper ID – IJTSRD39808 | Volume – 5 | Issue – 3 | March-April 2021 Page 330