You are on page 1of 10

See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/337472541

Embedded Optical Braille Recognition on Tamil Braille System using


Raspberry Pi

Article · November 2019

CITATIONS READS

6 204

2 authors, including:

Ajantha Devi
AP3 Solutions
8 PUBLICATIONS   27 CITATIONS   

SEE PROFILE

Some of the authors of this publication are also working on these related projects:

Braille to Speech and Speech to Braille View project

All content following this page was uploaded by Ajantha Devi on 23 November 2019.

The user has requested enhancement of the downloaded file.


ISSN:2229-6093

V Ajantha Devi et al, Int.J.Computer Technology & Applications,Vol 5 (4),1566-1574

Embedded Optical Braille Recognition on Tamil Braille System


using Raspberry Pi
1
Capt.Dr.S Santhosh Baboo, Associate Professor
2
V.Ajantha Devi, Ph.D Research Scholar

P.G.& Research Dept of Computer Science


D.G.Vaishnav College,
Chennai Tamilnadu, India.
1
santhos1968@gmail.com
2
ajay_press@rediffmail.com

Abstract

Optical Braille recognition is used to digitize and The written communications barrier between sighted
reproduce texts that have been produced with non- and visually impaired persons is particularly apparent
computerized systems, such as with Braille in the schooling system, where, nowadays, visually
typewriters. Digitizing Braille texts also helps reduce impaired students are taught in mainstream classes.
storage space, as Braille texts take up much more Many of these students perform assessment, tests and
space than their natural language counterparts. homework writing using the Braille system.
Editing and Reprinting of Braille document that were However, most staff of these students are not Braille
embossed on paper are time consuming and labour literate. Problems also exist in the workplace where
intensive. Optical Braille recognition is also useful any information written by a Braille user that is to be
for people who cannot read Braille, but need to interpreted by other Braille illiterate persons, needs to
access the content of Braille documents. This paper be first translated by the Braille user.
is on Methodology of a camera based assistive device To overcome this communications barrier, the
that can be used by people to read Braille document. device developed in this project provides a means by
The framework is on implementing image capturing which Braille illiterate persons can read what a
technique in an embedded system based on Braille user has written. The device is essentially a
Raspberry Pi board. hand held scanner that capture the image of the Tamil
Braille and converts into equivalent decoded Tamil
text which is capable of doing the extraction[24] of
1. Introduction Tamil Braille Character from a Braille document
followed by decoding them into Tamil Characters
The Braille system is a method that is used by
and then the decoded characters are normalized to
visually impaired people to read and write which is
Tamil text are also then converted into audio output.
invented in 1825 by Louis Braille. The preferred
means of communication for a visually impaired is
2. Tamil Braille System
through Tactile Braille system, where Tactile means
sense by touching or rubbing the surface of the The Braille system[9] comprises of a “cell” per
corresponding output device. character and these themselves consist of six
With the invention of computers, several embossed or raised dots arranged in a rectangle
approaches to computerized Braille translation have containing two columns of three dots each as shown
been developed and thus this makes computerized in Figure 1. A dot may be raised at any of the six
Braille[26] is a recently new phenomenon with the positions to form 2 6 (64) combinations (including the
Braille script. Many applications have been created combination in which no dots are raised). For
for translation from Braille to Speech. However, reference purposes, a particular combination may be
there is a shortage of programs designed for Tamil described by naming the positions where dots are
Braille. raised, the positions being universally numbered 1

IJCTA | July-August 2014 1566


Available online@www.ijcta.com
ISSN:2229-6093

V Ajantha Devi et al, Int.J.Computer Technology & Applications,Vol 5 (4),1566-1574

through 3 from top to bottom on the left, and 4 Headphone to deliver the output speech. The system
through 6 from top to bottom on the right. block diagram is shown in Figure 3.

Figure 1. Braille cell

The Braille code system has become widely used by


several communities because of its simplicity,
Figure 3. System Hardware Block Diagram
comfortable for blinds to use it when read and write.
Braille was applied or translated into several A. Raspberry pi
languages including Tamil language[16].
The Raspberry Pi[20] is a credit card sized
single-board computer developed in the UK by the
Raspberry Pi Foundation with the intention of
stimulating the teaching of basic computer science in
schools. Raspberry Pi contains a comprehensive
amount of features packed in a very reasonable price.
Raspberry Pi is constructed for Broadcom's
BCM2835 system around the circuit, which includes
a 700 MHz ARM11 family processor and include
250 MHz clock -frequency Broadcom's Video
Graphics Core IV. Memory B-model is 512 MB, and
it is divided into the graphics card.

Figure 2. Tamil Braille cell[1]

Tamil alphabet has descended from the Brahmi


script of ancient India. It is a syllabic language which
contains 12 vowels and 18 consonants in its script.
The vowels and consonants combine to form 216 Figure 4. View of Working Hardware system
compound characters, as this combination turns out
be in big number, two Braille cells are needed to B. Raspberry pi Camera
represent these combination. Thus only 38 cells have The camera module used in this project is
been assigned for Tamil Braille as shown in Figure 2. Raspberry PI NOIR (No IR) CAMERA BOARD[19]
as shown in the Figure 5. The camera plugs directly
3. System Hardware Design into the Camera Serial Interface (CSI) connector on
the Raspberry Pi. It‟s able to deliver clear 5MP
The whole system is composed by following parts:
resolution image, or 1080p HD video recording at
an image capturing camera[27][35], Raspberry Pi
30fps. The module attaches to Raspberry Pi, by way
board to run image recognition programs on it and a

IJCTA | July-August 2014 1567


Available online@www.ijcta.com
ISSN:2229-6093

V Ajantha Devi et al, Int.J.Computer Technology & Applications,Vol 5 (4),1566-1574

of a 15 pin Ribbon Cable, to the dedicated 15 pin camera.resolution = (1024, 768)


MIPI CSI, which was designed especially for
interfacing to cameras. The CSI bus is capable of camera.start_preview()
extremely high data rates, and it exclusively carries
# Camera warm-up time
pixel data to the BCM2835 processor.
time.sleep(2)
C. Enabling the camera
camera.capture('foo.jpg
Open the raspi-config tool from the Terminal:

sudo raspi-config
E. Storage (Memory)
1. Select Enable camera and hit Enter, The design does not include a built in hard disk or
2. then go to Finish and you'll be prompted to solid state drive, instead relying on an SD card for
reboot. booting and long term storage. This board is intended
to run Linux kernel based operating systems. This
Raspberry Pi module has a Samsung class 4 micro
SD card preloaded with the official Raspberry Pi
NOOBS (New Out of Box Software) package, and a
beautifully screen printed Micro SD card adaptor.
The system designed can be operated in two sessions,
ie one for capturing and creating a data base and the
other session is to capture the image and which can
be used for identifying or comparing the images in
the database.

4. System Software Design

The system that is able to translate a Braille script


Figure 5. Raspberry PI NOIR (No IR) CAMERA
into Tamil script and represents the converted script
BOARD
as text or voice to the user passes through several
This camera board which has no infrared filter stages including image capturing or scanning,
making it perfect for taking infrared photographs or converting the Image to Gray Level, image
photographing objects in low light (twilight) Thresholding (converting it to binary), de-skewing
conditions. Other features of this camera board are the image, edging the Braille dots, filling Braille dots,
Automatic image control functions Programmable opening the image by removing all micro scale
controls for frame rate 32 bytes of embedded one objects, cropping the cell frames, cropping the dot
time programmable (OTP) memory and Digital video frames from cell frames, generating binary equivalent
port (DVP) parallel output interface Excellent of activated Braille dots, generating equivalent
decimal Braille code, apply matching algorithm to
D. Take a picture Braille frames, get equivalent text and voice file of
The following code will take a single picture and
save it to 'foo.jpg'.

import time

import picamera

with picamera.PiCamera() as camera:

IJCTA | July-August 2014 1568


Available online@www.ijcta.com
ISSN:2229-6093

V Ajantha Devi et al, Int.J.Computer Technology & Applications,Vol 5 (4),1566-1574

matched Braille cell[28] stored in database.

Figure 7. scanned test image

ii) Converting the Image to Gray Level


Inside a computer system, colored images
are stored in 3-D arrays while gray level images are
stored in 2-D arrays. Dealing with 2-D arrays is much
easier and faster.

Figure 8. Gray level of Figure 7


Figure 6. System Software Block Diagram
Therefore, the first step in the proposed
Braille document is a page that written using system converts colour scanned images to gray level
Braille alphabets. In this project the design based on so that any pixel value in the image falls within the
standard specification of Tamil Braille writing, so to range 0- 255 .
make sure that the Braille page which used in
implementation will meet the standards iii) Cropping the Image Frame
specifications. The scanned images suffer from having
either black or white frames that would affect the
The test image has captured by using Raspberry thresholding step coming next. It is a must that those
PI NOIR (No IR) CAMERA BOARD and the image frames are cropped before proceeding forward. To do
store in JPEG format. that, the average gray level is calculated for the
whole image and then for each of the rows and
columns separately. Finding a row or column average
i) Image pre-processing gray level that is above or below 15% of the whole
Gray scale and binary conversion: Gray scale and image average gray level is an indication to delete it
binary conversion using rgb2gray and im2bw matlab as experiences have shown.
functions
iv) Image Thresholding

IJCTA | July-August 2014 1569


Available online@www.ijcta.com
ISSN:2229-6093

V Ajantha Devi et al, Int.J.Computer Technology & Applications,Vol 5 (4),1566-1574

An algorithm was developed to handle the


thresholding[33]. This algorithm works as follows;
after converting the image to gray level and removing
highest and lowest values to leave out distinct values,
the average gray level for the whole image[25] is
calculated.

Figure 12. Finding the deviation degree level

Crop effect on skewed Braille[29] image as


in Figure 11 evaluated. After determining the
deviation degree as in Figure 12, rotate the original
Figure 9 Image after adaptive thresholding
gray image and then Horizontal projection is
v) Image De-Skewing performed to count the number of pixels in each row
Thus a binary search algorithm was for the selected part in the previous step. Then the
developed to correct any de-skewing in tilted scanned rows having more than 10 pixel points was
images like Figure 10. The maximum degree of calculated.
recognizing a de-skewed image is 4 degrees from
either the left or the right side.

Figure 13. Cropping on skewed image

The image is rotated 4 degrees one time to


the left and one to the right for the rotated image as
Figure 10. Crop effect on skewed image by Figure 13. This is done because if the image is
skewed then cropping may remove some of the
image parts that constitute Braille cells as could be
seen in Figure 14.

Figure 11. Crop effect on skewed Braille image

Figure 14. Image after croppe and skewed

IJCTA | July-August 2014 1570


Available online@www.ijcta.com
ISSN:2229-6093

V Ajantha Devi et al, Int.J.Computer Technology & Applications,Vol 5 (4),1566-1574

vi) Dot Parts Detection viii) Braille letter recognition and transcription
Experiences have shown that detection of Braille dot In this stage of the project the Braille letter
[32] parts is better than detection of the whole dot. It was recognized using matching algorithm to match
was also proven that the average dot height is 8 each of the input decimal Braille code from an input
pixels. Each dot is composed of a bright and a dark processed image with codes of each Tamil letter by
region with a small space between them. Oyama et al. Figure 16. Then the image is converted to its decimal
[36] detected both the verso [34] (depression) and code representation:
recto (Protrusions) Braille dots utilizing shadow
patterns The testing image analyzed by using Single Decimal-Code=b1+b2*2+b3*4+b4*8+b5*16+ b6*32
side Braille Document by computing centroids on
After recognition process implemented the
dot[15].
recognized letter transcript into equivalent text file
through addressing process to run matched equivalent
files from stored addressed database.

Figure 16. ASCII Code for each cell

ix) Conversion to text


This is the last stage in implementation, the
word recognition process flow through letter
recognition[31] and fill Braille decimal array of
vii) Whole Dot Detection word, to apply matching process with stored
The framing process[30] to determine the addressed text files of words, then to run equivalent
cells, words and lines in the scanned image based on files from addressed word database
standard dimensions of Braille documents , the cell
frame size is known and experimentally recorded as Each Braille character is coded into a six bit
95X80 pixels in resolution of 200 dpi. Also the dot binary number based on the presence or absence of
size recorded as 20X15 pixels in resolution of 200 dots. The presence of a dot is indicated by 1 and its
dpi. absence by 0. This step is a simple one to one
mapping from a database containing the binary code
and the letter corresponding to this representation.

x) Text To Speech scope

The scope of this module is initiated with


the conclusion of the receding module of Braille
Recognition. The module performs the task of
conversion of the transformed Tamil text to audible
form.
Figure 15 shows the dots at the end of the search.

IJCTA | July-August 2014 1571


Available online@www.ijcta.com
ISSN:2229-6093

V Ajantha Devi et al, Int.J.Computer Technology & Applications,Vol 5 (4),1566-1574

The Raspberry Pi has an on-board audio


jack, the on-board audio is generated by a PWM
output and is minimally filtered. a USB audio card
can greatly improve the sound quality and volume.
Two options of attaching a microphone into
Raspberry Pi. One is to have USB mic, another to
have an external USB sound card.
To enable USB audio output, load the sound driver: Figure 18. Text conversion of the Figure 17

sudo modprobe snd_bcm2835

Enable USB audio output by default


sudo nano /etc/asound.conf

To playback: aplay test.wav

To adjust some volumes: alsamixer

5. Experimental Analysis
Figure 19. Braille image of a tilted document
The methodology used in this paper is
analysised by using the Tamil Braille System on
Thirukural Braille Book. Tirukkural is a classic
Tamil sangam literature consisting of 1330 couplets
or Kurals. It was authored by a Jain ascetic
Thiruvalluvar, a poet who is said to have lived
anytime between 2nd century BCE and 5th century
CE. This particularly apparent in the schooling
system. Following are the snapshots on result of the
analysis.

A couplet or Kural consists of seven cirs, with


four cirs on the first line and three on the second. A Figure 20. Text conversion of the Figure 19
cir is a single or a combination of more than one
Tamil word. For example, Thirukkural is a cir
formed by combining the two words Thiru and
Kural, i.e. Thiru + Kural = Thirukkural

Figure 21. Thirukural in 3 lines

The standard form of thirukural, couplet or


Kural consists of seven cirs, with four cirs on the
first line and three on the second. When embossed in
Braille format if the space in not sufficient for the
forth word in the first line, it is embossed in second
Figure 17. Braille image of 1st Kural
line as shown in the Figure 21 underline in blue and

IJCTA | July-August 2014 1572


Available online@www.ijcta.com
ISSN:2229-6093

V Ajantha Devi et al, Int.J.Computer Technology & Applications,Vol 5 (4),1566-1574

the three cirs in the second line be embossed in the Affordable System for the Sightless Population”,
third line. Asian Journal of Information Technology 6 (6):
2007, pp.696-699.
The Final process of the above methodology [6] Al-Salman(2003), “Towards a Computerized
is complete as the above text is synthesized and Arabic Braille environment,PDF”, King Saudi
converted in to audio format and played using University.
microphone or mini speaker connecting to on-board [7] Ebnet, Matthew (2001), "Braille Challenge
audio jack of Raspberry Pi. Gives Young Blind Students a Chance to Shine",
Los Angeles Times,
http://articles.latimes.com/2001/jun/30/local/me-
6. Conclusion 16960.
Dealing with images in term of image [8] State of Queensland (Department of
Education).(2000). Literate futures: Report of the
processing issue it is not an easy task. Adaptive
literacy review for Queensland state Schools,
thresholding technique that has been used to separate Queensland, Australia.
the Braille dots from the background is an effective [9] Swenson,A.M. (1999). “Beginning with Braille”.
technique and it gives a very good result for more NewYork: AFB Press.
than 90% from the images. Morphology techniques [10] P.Blenkhorn,"A System for Converting Braille
can help to enhance the image from a noise. The into Print," IEEE Transactionson Rehabilitation
captured image always has a skew angle (or the Engineering, vol.3, pp.215-221, 1995.
image has a rotated angle in 3rd axis). [11] Trent,S.D. &Truan, M.B (1997). “Speed,
accuracy, and comprehension of adolescent
Braille has been developed as the reading braille readers in a speialized school”. Journal of
and writing system for the visually impaired. The Visual Impairment and Blindness,91, pp.494-
attention was given on this is very difficult to teach a 500.
visually impaired people in the early stage and more [12] Mangold,S.S.(1999).”Trends in the use of Braille
training is needed for teaching them and converting Contractions in the United States: Implications
for UBC Decisions”. Unpublished manuscript.
Braille to text, is costly and cumbersome work.
[13] Millar,S.(1997). “Reading by Touch”.
7. Acknowledgment London:Routledge.
[14] Slaby W A(1990), “Computerized Braille
The author wish to thank the Christian Translation”, Microcomputer Applications,
Foundation for the Blind- India, Chennai for the Vol.13, pp.107-113.
support. The above paper is part of UGC Major [15] Nathan Altshiller-Court (2007), "College
Geometry", Dover Publications, (orig. Barnes &
Research Project of the Principal Investigator
Noble 1952), pp.70-71.
Capt.Dr.S Santhosh Baboo
[16] Capt.Dr.S Santhosh Baboo, V.Ajantha Devi;
"COMPUTER BASED TAMIL BRAILLE
8. Reference SYSTEM
[1] Bharati Braille URL – A Review";11th International Tamil Internet
Conference, Annamalai University,
http://acharya.iitm.ac.in/disabilities/bh_brl.php
Chidambaram, India , Jointly conducted by
[2] J.Bhattacharya, S.Majumder, G.Sanyal, International Forum for Information Technology
“Automatic inspection of Braille Character: A (INFITT) and Annamalai University Dec 28-30,
vision based approach.” International Journal of 2012. Pg.57 – 61
computer & Organization trends – Volume 1
[17] Capt.Dr.S Santhosh Baboo, V.Ajantha Devi;
Issue 3 – 2011.
"TAMIL BRAILLE SYSTEM: A Conversion
[3] BRL: Braille through Remote Learning -
methodology of Tamil into Contracted Braille
http://brl.org/refdesk/brlcont.html Script (Grade2)"; UACEE International Journal
[4] Abdallah M.Abualkishik, and Khairuddin Omar of Advances in Computer Science and its
“Quranic Baille System”, World Academy of Applications – IJCSIA Volume 3: Issue 2 [ISSN
Science, Engineering and Technology,4-6,2008. 2250 – 3765] Publication Date: 05 June 2013 –
[5] Mohammad Abu Yousu and S.M.Sai Shams, pg.72 -76
“Bangla Braille Inormation System: An

IJCTA | July-August 2014 1573


Available online@www.ijcta.com
ISSN:2229-6093

V Ajantha Devi et al, Int.J.Computer Technology & Applications,Vol 5 (4),1566-1574

[18] Capt.Dr.S Santhosh Baboo, V.Ajantha Devi; [28] Rawan Ismail Zaghloul and Tomader Jameel
"TAMIL BRAILLE SYSTEM: A Conversion Bani-Ata (2011), "Braille Recognition System –
methodology of Tamil into Contracted Braille With a Case Study Arabic Braille Documents",
Script (Grade2)"; Second Intl. Conf. on European Journal of Scientific Research, Vol. 62
Advances in Computer, Electronics and pp. 116-122.
Electrical Engineering -CEEE 2013, Institute of [29] Saad D. Al-Shamma, and Sami Fathi (2010),
Research Engineers and Doctors. ISBN: 978- "Arabic Braille Recognition and Transcription
981-07-6260-5 doi: 10.3850/ 978-981-07-6260- into Text and Voice", Proceedings of Biomedical
5_36. pg171 – 175. Engineering Conference (CIBEC), Cairo, Egypt,
[19] http://www.linuxcircle.com pp. 227-231.
[20] www.raspberrypi.org [30] Jan Mennens, Luc Van Tichelen, Guido
[21] Oi-Mean Foong and Nurul Safwanah Bt Mohd Francois, and Jan J. Engelen (1994), "optical
Razali, “Signage Recognition Framework for recognition of Braille writing using standard
Visually Impaired People”, 2011 International equipment", IEEE Transactions on Neural
Conference on Computer Communication and Systems and Rehabilitation Engineering, Vol. 2,
Management, Proc .of CSIT vol.5 IACSIT Press, No. 4, pp. 207-212.
Singapore, pg 488 – 492. [31] P. Blenkhorn (1997), "A system for converting
[22] Santanu Halder, Abul Hasnat, Amina Khatun, braille into print", IEEE Transactions on
Debotosh Bhattacharjee, Mita Nasipuri, Rehabilitation Engineering, Vol. 3, No. 2, pp.
“Development of a Bangla Character 215-221.
Recognition (BCR) System for Generation of [32] C. Ng, V. Ng, and Y. Lau (1999), "Regular
Bengali Text from Braille Notation”, Feature Extraction for Recognition of Braille",
International Journal of Innovative Technology Proceedings of the International Conference on
and Exploring Engineering (IJITEE) ISSN: Computational Intelligence and Multimedia
2278-3075, Volume-3, Issue-1, June 2013, pg 5 Applications, New Delhi, India, pp. 302-306.
- 10. [33] Lisa Wong, Waleed Abdulla, and Stephan
[23] Amany Al-Saleh, Ali El-Zaart and Abdul Malik Hussmann (2004), "A Software Algorithm
Al-Salman, “Dot Detection of Braille Images Prototype for Optical Recognition of Embossed
Using A Mixture of Beta Distributions”, Journal Braille", Proceedings of the International
of Computer Science 7 (11): 1749-1759, 2011, Conference on Pattern Recognition (ICPR),
ISSN 1549-3636, pg 1749 – 1759. Cambridge, UK, Vol. 2, pp. 586-589.
[24] Aisha Mousa, Hazem Hiary, Raja Alomari, and [34] X. Hermida, A. Corbacho Rodriguez, and F.
Loai Alnemer, “Smart Braille System Martin Rodriguez (1996), "A Braille O.C.R. for
Recognizer”, IJCSI International Journal of Blind People", Proceedings of the International
Computer Science Issues, Vol. 10, Issue 6, No 1, Conference on Signal Processing Applications &
November 2013, pg 52 – 60. Technology (ICSPAT 96), Vol. 1,. Boston, USA.
[25] Vidyashankar, G. Hemantha Kumar, and [35] Y. Mihara, A. Sugimoto, E. Shibayama, and S.,
P.Shivakumara (2004), "Rotation Invariant Takahashi (2005), "An Interactive Braille-
Histogram Features For Recognition Of Braille Recognition System for the Visually Impaired
Symbols", Proceedings of the International Based on a Portable Camera", Proceedings of
Conference on Cognitive Systems (ICCS „04), CHI Extended Abstracts on Human Factors in
New Delhi, India, pp. 32. Computing Systems, pp. 1653-1656.
[26] Avinash Chaudhary, Pardeep Garg, Arjun [36] Y. Oyama, T. Tajima, and H. Koga (1997),
Agarwal (2012), "Using Rotation Method for "Character Recognition of Mixed Convex-
Removal of Misalignment of Scanned Braille Concave Braille Points and Legibility of
Pattern", International Journal of Advancements Deteriorated Braille Points", System and
in Electronics and Electrical Engineering Computer in Japan, Vol. 28, No. 2, pp. 44-53.
(IJAEEE), Vol. 1, No. 2, pp. 145-149.
[27] .Iain Murray, and Andrew Pasquale (2006), "A
Portable Device for the Translation of Braille to
Literary Text", Proceedings of ACM Conference
on Assistive Technologies (ASSETS), pp. 231-
232.

IJCTA | July-August 2014 1574


Available online@www.ijcta.com
View publication stats

You might also like