REVIEW-3

EEE2004-MEASUREMENT & INSTRUMENTATION

Dr. GUNABALAN R

20BEE1052- ANAMITRA MAITI

20BEE1177-RAKESH K
20BEE1179- MOHAMMED ABDUL AZHARUDDIN A
20BEE1183- ARSHAD HAMEED S

06/12/2021 EEE2004 J COMPONENT PROJECT 1

 OPTICAL CHARACTER RECOGNITION
SPEECH SYNTHESIS SYSTEM

Using LabVIEW

06/12/2021 EEE2004 J COMPONENT PROJECT 2

 INTRODUCTION
Machine replication of human functions, like reading, is an ancient dream.
However, over the last five decades, machine reading has grown from a dream to
reality. Character recognition or optical character recognition (OCR), is the
process of converting scanned images of machine printed or handwritten text
(numerals, letters, and symbols), into a computer format text (such as ASCII).
Optical character recognition has become one of the most successful applications
of technology in the field of pattern recognition and artificial intelligence. Many
commercial systems for performing OCR exist for a variety of applications.
Speech is probably the most efficient medium for communication between
humans, A Text-To-Speech (TTS) synthesizer is a computer-based system that
should be able to read any text aloud, whether it was directly introduced in the
computer by an operator or scanned and submitted to an Optical Character
Recognition (OCR) system.

06/12/2021 EEE2004 J COMPONENT PROJECT 3

 SOFTWARE REQUIRED

LabVIEW

Laboratory Virtual Instrument Engineering Workbench (LabVIEW) is a system-design platform

and development environment for a visual programming language from National Instruments.
The graphical language is named "G"; not to be confused with G-code. The G dataflow language
was originally developed by Labview, LabVIEW is commonly used for data acquisition,
instrument control, and industrial automation on a variety of operating systems (OSs), including
Microsoft Windows as well as various versions of Unix, Linux, and macOS.ble

06/12/2021 EEE2004 J COMPONENT PROJECT 4

 OBJECTIVE

The main objective of this Project is to:

1) Study Optical character recognition technology.

2) Study the speech synthesis technology.
3) Develop Optical character recognition using LabVIEW software.
4) Develop text to speech module using LabVIEW software.
5) Training the OCR System to recognize characters from large database.

06/12/2021 EEE2004 J COMPONENT PROJECT 5

 BLOCK REPRESENTATION

Optical character recognition (OCR) is the

mechanical or electronic translation of images
of hand-written or printed text into machine-
OCR
editable text. The OCR based system consists
of Image Acquisition, Image Pre-processing
(Binarization), Image Segmentation, Matching
and Recognition.

06/12/2021 EEE2004 J COMPONENT PROJECT 6

 BLOCK REPRESENTATION

Speech Synthesis
TEXT ANALYSIS & PHONETIC
INPUT RECOGNITION ANALYSIS

SYNTHESIZED CONCANTENATION OF SPEECH

SPEECH SPEECH UNITS DATABASE

06/12/2021 EEE2004 J COMPONENT PROJECT 7

 FLOW CHART

06/12/2021 EEE2004 J COMPONENT PROJECT 8

 CIRCUIT DIAGRAM

06/12/2021 EEE2004 J COMPONENT PROJECT 9

 CIRCUIT DIAGRAM

06/12/2021 EEE2004 J COMPONENT PROJECT 10

 NI-IMAQdx NI-IMAQ Vision Utilities
The NI-IMAQdx VI library part of the The NI-IMAQ VI library part of the NI- Use the Vision Utilities VIs to create and
NI-IMAQdx software is a group of IMAQdx software is a group of virtual manipulate images in NI Vision.
virtual instruments (VIs) that enable instruments (VIs) that enable you to use
you to use LabVIEW with your camera. LabVIEW with your camera. Mostly
not recommended to use as it may cause
some errors
IMAQdx Open Camera VI IMAQdx Close Camera VI
Opens a camera, queries the
camera for its capabilities, loads Stops an acquisition in progress, releases
a camera configuration file, and
creates a unique reference to the
FUNCTIONS USED resources associated with an acquisition, and
closes the specified Camera Session.
camera

Image Processing Machine Vision Vision Express

Use the Image Processing VIs Use the Machine Vision VIs to perform common
Use the Vision Express VIs to
to analyze, filter, and process machine vision inspection tasks, including the
quickly develop common image
images in NI Vision. presence or absence of parts in an image and
acquisition and processing
measuring the dimensions of parts to see if they
applications.
meet specifications.

06/12/2021 EEE2004 J COMPONENT PROJECT 11

 FUNCTIONS USED
Session In NI Vision Control Palette
Vision Assistant Express VI
: specifies the name of the camera
you wish to open. The default Use NI Vision Assistant from within The Vision controls palette is available
value is cam0 the LabVIEW environment to perform from the top level of the LabVIEW
common image processing tasks. Controls palette.
IMAQdx Configure (This function runs only for trail upto
Grab VI 45 days in labview).
Configures and starts a grab acquisition. A
grab performs an acquisition that loops Image Display Vision Control
continually on a ring of buffers. Use the IMAQdx Grab VI
grab VI for high-speed image acquisition.
Acquires the most current frame into Image Use this control to display your images
Out. Call this VI only after calling IMAQdx directly on the LabVIEW. You also can
Image Processing Configure Grab VI. If the image type does not use this control to create regions of
match the video format of the camera, this VI interest (ROIs). Both Classic and 3D
Use the Image Processing VIs to analyze, changes the image type to a suitable format. versions of the Image Display control are
filter, and process images in NI Vision. available.

06/12/2021 EEE2004 J COMPONENT PROJECT 12

 While Loop Structure
A While Loop is structure you use to execute a block of code repeatedly until a
given condition is met. When the VI runs, the code inside the While Loop executes,
and then the terminal condition is evaluated

FUNCTIONS USED

06/12/2021 EEE2004 J COMPONENT PROJECT 13

 FUNCTIONS USED

.NET Function Constructor Node Text/String Control

Indicator
They are used to create .NET objects, set It Creates an instance of a .NET object.
properties or call methods on those This node identifies the constructor Use string controls and indicators to
objects, and handle events for those from which to create a .NET object. enter or display text.
objects in the .NET environment

.NET Object to Variant VI Read Text File File Path Control

NET Object is the .NET object you want Reads a specified number of characters A file path control, shown as follows, is
to convert to a LabVIEW variant. or lines from a byte stream file. This a LabVIEW data type that identifies
function does not work for files the location of a file on disk.
inside an LLB

06/12/2021 EEE2004 J COMPONENT PROJECT 14

 FUNCTIONS USED

IMAQ Convert Rectangle to ROI VI IMAQ OCR Read Text 4 VI IMAQ OCR Read Character Set File VI
Converts a rectangle or rotated rectangle
Reads the text in the image. The VI identifies all objects in Reads a character set and session properties from the
to an ROI Descriptor. The contour of
the image based on the properties that you set, and then character set file specified by File Path. The VI
the ROI Descriptor returned is compares each object with every character in the adds the character set to the trained character set
always of the type rotated rectangle. character set file. For each object, the VI selects the that the IMAQ OCR Read Text 4 VI uses during
character that most closely matched the object. The VI the reading process.
uses the substitution character for any object that did
not match any of the trained characters.

IMAQ OCR Create Session VI

Creates an OCR session and returns a IMAQ Overlay ROI VI
refnum associated with the session. Overlays a region of interest
(ROI) on an image.

06/12/2021 EEE2004 J COMPONENT PROJECT 15

 SIMULATION & RESULTS
Text training block diagram

06/12/2021 EEE2004 J COMPONENT PROJECT 16

 SIMULATION & RESULTS
Text training results

06/12/202 EEE2004 J COMPONENT PROJECT 17

 SIMULATION & RESULTS
Text training results

06/12/2021 EEE2004 J COMPONENT PROJECT 18

 SIMULATION & RESULTS
Text Scanning Block Diagram

06/12/202 EEE2004 J COMPONENT PROJECT 19

 SIMULATION & RESULTS
Text Scanning Results

06/12/2021 EEE2004 J COMPONENT PROJECT 20

 SIMULATION & RESULTS
OCR based Text Scanning System

06/12/2021 EEE2004 J COMPONENT PROJECT 21

 REFERENCE
1) T.Dutoit, "High quality text-to-speech synthesis: a comparison of four candidate algorithms," Acoustics, Speech, and
Signal Processing, 1994. ICASSP-94., 1994 IEEE International Conference on, vol.i, no., pp.I/565-I/568 vol.1, 19-22 Apr
1994.

2) B.M. Sagar, Shobha G, R. P. Kumar, “OCR for printed Kannada text to machine editable format using database
approach” WSEAS Transactions on Computers Volume 7, Pages 766-769, 6 June 2008.

3) G. Nagy, "At the frontiers of OCR," Proceedings of the IEEE, vol.80, no.7, pp.1093- 1100, Jul 1992.

4) J. Flanagan, “Speech Analysis, Synthesis, and Perception,” Springer-Verlag, Berlin- Heidelberg-New York, 1972.

5) W. Hallahan. “DECtalk Software: Text-to-Speech Technology and Implementation,” Digital Technical Journal, 1996.

6) M. Sarfraz; S.A. Shahab, "An efficient scheme for tilt correction in Arabic OCR system," Computer Graphics, Imaging
and Vision: New Trends, 2005. International Conference on, vol., no., pp. 379-384, 26-29 July 2005.

7) J. Allen, S. Hunnicutt, D. Klatt. “From Text to Speech,” The MITalk System. Cambridge University Press, Inc., 1987.
CES

06/12/2021 EEE2004 J COMPONENT PROJECT 22

 THANK YOU

06/12/2021 EEE2004 J COMPONENT PROJECT 23