Optical Character Recognition System for Document Processing

1. INTRODUCTION
In the running world, there is growing demand for the software systems to recognize
characters in computer system when information is scanned through paper documents as we
know that we have number of newspapers and books which are in printed format related to
different subjects. These days there is a huge demand in “storing the information available
in these paper documents in to a computer storage disk and then later reusing this
information by searching process”. One simple way to store information in these paper
documents in to computer system is to first scan the documents and then store them as
IMAGES. But to reuse this information it is very difficult to read the individual contents
and searching the contents form these documents line-by-line and word-by-word. The
reason for this difficulty is the font characteristics of the characters in paper documents are
different to font of the characters in computer system. As a result, computer is unable to
recognize the characters while reading them. This concept of storing the contents of paper
documents in computer storage place and then reading and searching the content is called
DOCUMENT PROCESSING. Sometimes in this document processing we need to process
the information that is related to languages other than the English in the world. For this
document processing we need a software system called CHARACTER RECOGNITION
SYSTEM. This process is also called DOCUMENT IMAGE ANALYSIS (DIA).
Thus our need is to develop character recognition software system to perform Document
Image Analysis which transforms documents in paper format to electronic format. For this
process there are various techniques in the world. Among all those techniques we have
1

chosen Optical Character Recognition as main fundamental technique to recognize
characters. The conversion of paper documents in to electronic format is an on-going task
in many of the organizations particularly in Research and Development (R&D) area, in
large business enterprises, in government institutions, so on. From our problem statement
we can introduce the necessity of Optical Character Recognition in mobile electronic
devices such as cell phones, digital cameras to acquire images and recognize them as a part
2
of face recognition and validation.
To effectively use Optical Character Recognition for character recognition in-order to
perform Document Image Analysis (DIA), we are using the information in Grid format. .
This system is thus effective and useful in Virtual Digital Library’s design and
construction.
1.1 PURPOSE
The main purpose of Optical Character Recognition (OCR) system based on a grid
infrastructure is to perform Document Image Analysis, document processing of electronic
document formats converted from paper formats more effectively and efficiently. This
improves the accuracy of recognizing the characters during document processing compared
to various existing available character recognition methods. Here OCR technique derives
the meaning of the characters, their font properties from their bit-mapped images.
 The primary objective is to speed up the process of character recognition in document
processing. As a result the system can process huge number of documents with-in less
time and hence saves the time.

 Since our character recognition is based on a grid infrastructure, it aims to recognize
multiple heterogeneous characters that belong to different universal languages with
3
different font properties and alignments.
1.2 PROJECT SCOPE
The scope of our product Optical Character Recognition on a grid infrastructure is to
provide an efficient and enhanced software tool for the users to perform Document Image
Analysis, document processing by reading and recognizing the characters in research,
academic, governmental and business organizations that are having large pool of
documented, scanned images. Irrespective of the size of documents and the type of
characters in documents, the product is recognizing them, searching them and processing
them faster according to the needs of the environment.
1.3 EXISTING SYSTEM
In the running world there is a growing demand for the users to convert the printed
documents in to electronic documents for maintaining the security of their data. Hence the
basic OCR system was invented to convert the data available on papers in to computer
process able documents, So that the documents can be editable and reusable. The existing
system/the previous system of OCR on a grid infrastructure is just OCR without grid
functionality. That is the existing system deals with the homogeneous character recognition
or character recognition of single languages.

1.4 DRAWBACK OF EXISTING SYSTEM
The drawback in the early OCR systems is that they only have the capability to convert and
recognize only the documents of English or a specific language only. That is, the older
4
OCR system is uni-lingual.
1.5 PROPOSED SYSTEM
Our proposed system is OCR on a grid infrastructure which is a character recognition
system that supports recognition of the characters of multiple languages. This feature is
what we call grid infrastructure which eliminates the problem of heterogeneous character
recognition and supports multiple functionalities to be performed on the document. The
multiple functionalities include editing and searching too where as the existing system
supports only editing of the document. In this context, Grid infrastructure means the
infrastructure that supports group of specific set of languages. Thus OCR on a grid
infrastructure is multi-lingual.
1.6 BENEFIT OF PROPOSED SYSTEM
The benefit of proposed system that overcomes the drawback of the existing system is that
it supports multiple functionalities such as editing and searching. It also adds benefit by
providing heterogeneous characters recognition.

1.7 ARCHITECTURE OF THE PROPOSED SYSTEM
The Architecture of the optical character recognition system on a grid infrastructure
consists of the three main components. They are:-
5
 Scanner
 OCR Hardware or Software
 Output Interface
Figure.1: OCR Architecture

1.8 INTENDED AUDIENCE AND READING SUGGESTIONS
In this section, we identify the audience who are interested with the product and are
involved in the implementation of the product either directly or indirectly. As from our
research, the OCR system is mainly useful in R&D at various scientific organizations, in
governmental institutes and in large business organizations, we identify the following as
various interested audience in implementing OCR system:-
 The scientists, the research scholars and the research fellows in telecommunication
institutions are interested in using OCR system for processing the word document
that contains base paper for their research.
 The Librarian to manage the information contents of the older books in building
virtual digital library requires use of OCR system.
 Various sites that vendor e-books have a huge requirement of this OCR system in-order
to scan all the books in to electronic format and thus make money. The
Amazon book world is largely using this concept to build their digital libraries.
Now we present the reading suggestions for the users or clients through which the user can
better understand the various phases of the product. These suggestions may be effective and
useful for the beginners of the product rather than the regular users such as research
scholars, librarians and administrators of various web-sites. With these suggestions, the user
need not waste his time in scrolling the documents up and down, browsing through the web,
visiting libraries in search of different books and … The following are the various reading
suggestions that the user can follow in-order to completely understand about our product
6
and to save time:-

 It would help you if you start with Wikipedia.com. It lets you know the basic
concept of every keyword you require. First learn from it what is OCR? And how
does it work based on a Grid infrastructure?
 Now you can proceed your further reading with the introduction of our product we
provided in our documentation. From these two steps you completely get an in-depth
idea of the use of our product and several processes involved in it.
 The more you need is the implementation of the product. For this you can visit
FreeOCR.com where you can view how the sample OCR works and you can try it.
7

2. FEASIBILITY STUDY
A feasibility study is a high-level capsule version of the entire System analysis and Design
Process. The study begins by classifying the problem definition. Feasibility is to determine
if it’s worth doing. Once an acceptance problem definition has been generated, the analyst
develops a logical model of the system. A search for alternatives is analyzed carefully.
8
There are 3 parts in feasibility study.
2.1 TECHNICAL FEASIBILITY
Evaluating the technical feasibility is the trickiest part of a feasibility study. This is because,
at this point in time, not too many detailed design of the system, making it difficult to
access issues like performance, costs on (on account of the kind of technology to be
deployed) etc. A number of issues have to be considered while doing a technical analysis.
Understand the different technologies involved in the proposed system before commencing
the project we have to be very clear about what are the technologies that are to be required
for the development of the new system. Find out whether the organization currently
possesses the required technologies. Is the required technology available with the
organization?.
2.2 OPERATIONAL FEASIBILITY
Proposed project is beneficial only if it can be turned into information systems that will
meet the organizations operating requirements. Simply stated, this test of feasibility asks

if the system will work when it is developed and installed. Are there major barriers to
Implementation? Here are questions that will help test the operational feasibility of a
9
project:
 Is there sufficient support for the project from management from users? If the current
system is well liked and used to the extent that persons will not be able to see reasons
for change, there may be resistance.
 Are the current business methods acceptable to the user? If they are not, Users may
welcome a change that will bring about a more operational and useful systems.
 Have the user been involved in the planning and development of the project?
 Early involvement reduces the chances of resistance to the system and in general and
increases the likelihood of successful project.
Since the proposed system was to help reduce the hardships encountered. In the existing
manual system, the new system was considered to be operational feasible.
2.3 ECONOMIC FEASIBILITY
Economic feasibility attempts to weigh the costs of developing and implementing a new
system, against the benefits that would accrue from having the new system in place. This
feasibility study gives the top management the economic justification for the new system. A
simple economic analysis which gives the actual comparison of costs and benefits are much
more meaningful in this case. In addition, this proves to be a useful point of reference to
compare actual costs as the project progresses. There could be various types of intangible

benefits on account of automation. These could include increased customer satisfaction,
improvement in product quality better decision making timeliness of information,
expediting activities, improved accuracy of operations, better documentation and record
keeping, faster retrieval of information, better employee morale.
10
2.4 TRAINING
Training is a very important process of working with a neural network. As seen from neural
networks, there are two forms of training that can be employed with a neural network. They
are namely:-
1. Un-Supervised Training
2. Supervised Training
Supervised training provides the neural network with training sets and the anticipated
output. Unsupervised training supplies the neural network with training sets, but there is no
anticipated output provided.
2.4.1 UNSUPERVISED TRAINING
Unsupervised training is a very common training technique for Kohonen neural networks.
We will discuss how to construct a Kohonen neural network and the general process for
training without supervision.

What is meant by training without supervision is that the neural network is provided with
training sets, which are collections of defined input values. But the unsupervised neural
network is not provided with anticipated outputs.
Unsupervised training is usually used in a classification neural network. A classification
neural network takes input patterns, which are presented to the input neurons. These input
patterns are then processed, and one single neuron on the output layer fires. This firing
neuron can be thought of as the classification of which group the neural input pattern
belonged to. Handwriting recognition is a good application of a classification neural
11
network.
The input patterns presented to the Kohonen neural network are the dot image of the
character that was hand written. We may then have 26 output neurons, which correspond to
the 26 letters of the English alphabet. The Kohonen neural network should classify the
input pattern into one of the 26 input patterns.
During the training process the Kohonen neural network in handwritten recognition is
presented with 26 input patterns. The network is configured to also have 26 output patterns.
As the Kohonen neural network is trained the weights should be adjusted so that the input
patterns are classified into the 26 output neurons. This technique results in a relatively
effective method for character recognition.
Another common application for unsupervised training is data mining. In this case you
have a large amount of data, but you do not often know exactly what you are looking for.
You want the neural network to classify this data into several groups. You do not want to
dictate, ahead of time, to the neural network which input pattern should be classified to

which group. As the neural network trains the input patterns will fall into similar groups.
This will allow you to see which input patterns were in common groups.
12
2.4.2 SUPERVISED TRAINING
The supervised training method is similar to the unsupervised training method in that
training sets are provided. Just as with unsupervised training these training sets specify
input signals to the neural network.
The primary difference between supervised and unsupervised training is that in supervised
training the expected outputs are provided. This allows the supervised training algorithm to
adjust the weight matrix based on the difference between the anticipated output of the
neural network, and the actual output.
There are several popular training algorithms that make use of supervised training. One of
the most common is the back-propagation algorithm. It is also possible to use an algorithm
such as simulated annealing or a genetic algorithm to implement supervised training
2.5 INTRODUCING KOHONEN NEURAL NETWORK
The Kohonen neural network differs considerably from the feed-forward back propagation
neural network. The Kohonen neural network differs both in how it is trained and how it
recalls a pattern. The Kohonen neural network does not use any sort of activation function.
Further, the Kohonen neural network does not use any sort of a bias weight.

Output from the Kohonen neural network does not consist of the output of several neurons.
When a pattern is presented to a Kohonen network one of the output neurons is selected as
a "winner". This "winning" neuron is the output from the Kohonen network. Often these
"winning" neurons represent groups in the data that is presented to the Kohonen network.
For example, in an OCR program that uses 26 output neurons, the 26 output neurons map
the input patterns into the 26 letters of the Latin alphabet.
The most significant difference between the Kohonen neural network and the feed forward
back propagation neural network is that the Kohonen network trained in an unsupervised
mode. This means that the Kohonen network is presented with data, but the correct output
that corresponds to that data is not specified. Using the Kohonen network this data can be
classified into groups. We will begin our review of the Kohonen network by examining the
13
training process.
It is also important to understand the limitations of the Kohonen neural network. Neural
networks with only two layers can only be applied to linearly separable problems. This is
the case with the Kohonen neural network. Kohonen neural networks are used because they
are a relatively simple network to construct that can be trained very rapidly.
A "feed forward" neural network is similar to the types of neural networks that we are ready
examined. Just like many other neural network types the feed forward neural network
begins with an input layer. This input layer must be connected to a hidden layer. This
hidden layer can then be connected to another hidden layer or directly to the output layer.
There can be any number of hidden layers so long as at least one hidden layer is provided.
In common use most neural networks will have only one hidden layer. It is very rare for a

neural network to have more than two hidden layers. We will now examine, in detail, and
the structure of a "feed forward neural network".
The Structure of a Feed Forward Neural Network
A "feed forward" neural network differs from the neural networks previously examined.
Figure 2.1 shows a typical feed forward neural network with a single hidden layer.
Figure 2 Feed Forward Neural Network
14
The Input Layer
The input layer to the neural network is the conduct through which the external
environment presents a pattern to the neural network. Once a pattern is presented to the
input layer of the neural network the output layer will produce another pattern. In essence
this is all the neural network does. The input layer should represent the condition for which

we are training the neural network for. Every input neuron should represent some
independent variable that has an influence over the output of the neural network.
It is important to remember that the inputs to the neural network are floating point numbers.
These values are expressed as the primitive Java data type "double". This is not to say that
you can only process numeric data with the neural network. If you wish to process a form
of data that is non-numeric you must develop a process that normalizes this data to a
15
numeric representation.
The Output Layer
The output layer of the neural network is what actually presents a pattern to the external
environment. Whatever patter is presented by the output layer can be directly traced back to
the input layer. The number of a output neurons should directly related to the type of work
that the neural network is to perform.
To consider the number of neurons to use in your output layer you must consider the
intended use of the neural network. If the neural network is to be used to classify items into
groups, then it is often preferable to have one output neurons for each groups that the item
is to be assigned into. If the neural network is to perform noise reduction on a signal then it
is likely that the number of input neurons will match the number of output neurons. In this
sort of neural network you would one day he would want the patterns to leave the neural
network in the same format as they entered.
For a specific example of how to choose the numbers of input and output neurons consider
a program that is used for optical character recognition, or OCR. To determine the number

of neurons used for the OCR example we will first consider the input layer. The number of
input neurons that we will use is the number of pixels that might represent any given
character. Characters processed by this program are normalized to universal size that is
represented by a 5x7 grid. A 5x7 grid contains a total of 35 pixels. The optical character
recognition program therefore has 35 input neurons.
The number of output neurons used by the OCR program will vary depending on how many
characters the program has been trained for. The default training file that is provided with
the optical character recognition program is trained to recognize 26 characters. As a result
using this file the neural network would have 26 output neurons. Presenting a pattern to the
input neurons will fire the appropriate output neuron that corresponds to the letter that the
16
input pattern corresponds to.

3.SOFTWARE REQUIREMENT ANALYSIS
17
3.1 PROBLEM STATEMENT
The problem here is for the software systems to recognize characters in computer system
when information is scanned through paper documents as we know that we have number of
newspapers and books which are in printed format related to different subjects. Whenever
we scan the documents through the scanner, the documents are stored as images such as
jpeg, gif etc., in the computer system. These images cannot be read or edited by the user.
But to reuse this information it is very difficult to read the individual contents and searching
the contents form these documents line-by-line and word-by-word. These days there is a
huge demand in “storing the information available in these paper documents in to a
computer storage disk and then later editing or reusing this information by searching
process”.
3.2 MODULES AND THEIR FUNCTIONALITIES
Our software system Optical Character Recognition on a grid infrastructure can be divided
into five modules based on its functionality.The modules classified are as follows:-
 Document Processing Module
 System Training Module.
 Document Recognition Module.
 Document Editing Module and

18
 Document Searching Module.
3.2.1 DOCUMENT PROCESSING MODULE
This module is accessed by administrator whose role in our application is a librarian.This
module perform certain activities such as scanning documents, storing them as images,
recognizing characters in images to transfer them into word format. During the recognition
process, this module uses the OCR methodology in support of grid infrastructure
datastructure. The module supports the following services:-
 Scanning printed documents.
 Storing the documents as snapshots or images.
 Processing those image-based documents.
 Converting these image-based documents into e-documents(also called structured
documents).
 Recognizing the characters in documents.
 Generating grid infrastructure datastructure.
3.2.2 SYSTEM TRAINING MODULE
This module can be accessed by both the administrator and the end-user. Before converting
the printed documents in to editable and searchable documents, the first and the mandatory
step is providing training to the system. Here training in the sense the font followed in the
scanned document should be identified by the user. Then the user types all the characters
that are required for recognition from the scanned document as an image file. This image
file should be provided as an input during the training process. The user then clicks the train

button provided in the recognition module. Then the training gets completed. Thus the
system gets familiar with the new font. This module supports:-
 Training the system with the pre-defined fonts.
 Training the system with the new fonts that are not present in the system and that
19
cannot be identified by the system.
3.2.3 DOCUMENT RECOGNITION MODULE
This module can be accessed by both the administrator and the end-user. Once the printed
documents are converted into structured documents, any user can recognize the characters
present in the document. That means the user can recognize the characters of any language
he chooses which makes OCR more flexible. This flexibility is due to the adaptation of grid
infrastructure. This is the module where the main functionality of OCR is tested.
Under this module, there are two types of recognition. They are handwritten recogniiton
and scanned document recognition.
In handwritten recognition, the handwriting of the user in any language is trained to the
system only for the first time. From there on-wards, the system recognizes the characters or
words written by the user. Thus handwritten document recognition recognizes the human
handwriting.
In scanned document recognition, the system is first trained with the font characters in the
document in the training module itself. Now in the recognition module, the system takes the
scanned documents image as an input file, first crops the image and then
extracts/recognizes the characters from the document and makes these documents editable
and searchable. Thus the scanned document recognition recognizes the chracters from the

scanned document image and makes the document editable and searchable. Hence the
document recogniiton module on a whole supports the following services:-
 Converts the document into specific format
20
 Recognizes the characters
 Heterogeneous character Recognition
3.2.4 DOCUMENT EDITING MODULE
This module can be accessed by both the administrator and the end-user during document
editing to implement the character recogniiton process. Once the scanned documents are
stored, they reside in computer memory. This data resides in the form of an image that is
just viewable in an image viewer. Hence, the document is first coverted into a form such
that it is editable. The desired form of the document may be MS-Word,Text,… as specified
by the user.The objective of this module is to let the user perform :-
 Addition of specific content to the documents
 Deletion of certain content from documents
 Any other modification of documents.
3.2.5 DOCUMENT SEARCHING MODULE
This module can be accessed by both the administrator and the end-user during the search
of the user required document to implement the character recogniiton process on it. The
user requests the system to search for a particular document. Then the system finds the
documents based on OCR methodology and returns the result of the search to the user.

4. SOFTWARE DESIGN
21
4.1 DATA FLOW DIAGRAM
The DFD is also called as bubble chart. A data-flow diagram (DFD) is a graphical
representation of the "flow" of data through an information system. DFD’s can also be used
for the visualization of data processing. The flow of data in our system can be described in
the form of dataflow diagram as follows:-
1. Firstly, if the user is administrator he can initialize the following actions:-
 Document processing
 Document search
 Document editing.
All the above actions come under 2cases.They are described as follows:-
a) If the printed document is a new document that is not yet read into the system, then the
document processing phase reads the scanned document as an image only and then
produces the document image stored in computer memory as a result.
Now the document processing phase has the document at its hand and can read the
document at any point of time. Later the document processing phase proceeds with
recognizing the document using OCR methodology and the grid infrastructures. Thus it
produces the documents with the recognized characters as final output which can be
later searched and edited by the end-user or administrator.
b) If the printed document is already scanned in and is held in system memory, then the
document processing phase proceeds with document recognition using OCR

methodology and grid infrastructure. And thus it finally produces the document with
22
recognized documents as output.
2. If the user using the OCR system is the end-user, then he can perform the following
actions:-
 Document searching
 Document editing
1. Document Searching:- The documents which are recognized can be searched by the
user whenever required by requesting from the system database.
2. Document Editing:- The recognized documents can be edited by adding the specific
content to the document, deleting specific content from the document and modifying the
document.

Document
Processing
Use
OCR
Recognize
Document
Figure 3:Data Flow Diagram
23
Scan
images
Store
images
Read
docume
nts
Modify
Use
Grid
Delete
Recognize
Document
Edit
Document
Document
Search
User
Document
as image

24
4.2 UML DIAGRAMS
UML combines best techniques from data modeling (entity relationship diagrams),
business modeling (work flows), object modeling, and component modeling. It can be used
with all processes, throughout the software development life cycle, and across different
implementation technologies. UML has 14 types of diagrams divided into two categories.
Seven diagram types represent structural information, and the other seven represent general
types of behavior, including four that represent different aspects of interactions. Some of
these diagrams we provided to describe the design and implementation of our OCR system
can be categorized hierarchically as below:-
 Use case diagram
 Class diagram
 Sequence diagram
 Collaboration diagram
 Activity diagram
 Component diagram
 Deployment diagram
4.2.1 USE-CASE DIAGRAMS
Our software system can be used to support library environment to create a Digital Library
where several paper documents are converted into electronic-form for accessing by the
users. For this purpose the printed documents must be recognized before they are converted
into electronic-form. The resulting electronic-documents are accessed by the users like

faculty and students for reading and editing. Now according to this information, the
following are the different actors involved in implementing our OCR system:-
 If we consider for virtual digital library, the Administrator can be the Librarian and
the End-users can be Students or/and Faculty.
 The following are the list of use diagrams that altogether form the complete or the
overall use-case diagram. They are listed below:-
1. Use-case diagram for document processing
2. Use-case diagram for neural network training
3. Use-case diagram for document recognition
4. Use-case diagram for document editing
5. Use-case diagram for document searching
In each of the use-case diagrams below we clearly explained about that particular use-case
functionality. In this we provided a description about the
25
 Use-case name
 Details about the use-case
 Actors using this use-case
 The flow of events carried out by the use-case
 The conditions that occur in this use-case

Figure 4 :Use-Case Diagram For Document Processing
26
Use Case Name
Document processing
Description
The administrator is the only person who participates in the document processing. Here he
scans the documents. The scanned documents are read as images. Finally the read images
are stored in the system memory.
Actors
 Primary Actor : Administrator
 Secondary Actor : User
Scans documents
read images
stores the images
Administrator

27
Flow of Events
1. The Administrator scans the document which he wants to edit.
2. The scanned documents are read as images.
3. Finally the images that are read are stored in system memory for the future
reference.
Figure 5:Use-Case Diagram For Neural Network Training
Use case Name
Neural Network Training
Description
The Administrator or End-user enters the specific characters required for training. User
stores them as image file and trains the system.
Enters specific characters
Stores them as image file
Trains the system
Administrator or
end-user

28
Actors
 Primary Actor : Administrator or End-user
Flow of Events
1. The user enters the specific characters in order to train the system.
2. After entering it is stored as image file.
3. Finally trains the system according to the system.
Pre-Condition
The font in the scanned document should be identified.
Open document in editor
Select Edit action
Performs editing
Stores edited document
Administrator or
End-user
Figure 6 Use-Case Diagram For Document Editing

29
Use case Name
Document editing
Description
Both Administrator and End-user can perform the document editing. The user opens the
document in the editor and selects the edit action i.e., edit, modify, delete etc. After
selecting the edit action editing operation is performed and finally stores the document that
had been edited.
Actors
Flow of Events
1. The Administrator or End-user opens the document which he want to edit.
2. He selects the edit action. The action consists of editing the document, modifying
the document, deleting the document etc.
3. After selecting the edit action the editing operation is performed.
4. Finally the edited document is stored in the system memory.
Pre-Condition
The input to be taken for editing should be an image of the document that is converted in to
word or text file. That is the input file must be either .doc file or .txt file only.

30
Post-Condition
Finally after editing the document there are specific target formats defined by the user. The
document should be saved in that format only. That will be the output of the editor. That is,
as per our design the final document after editing must be saved in .doc file or .txt file only.
Figure 7:Use-Case Diagram For Document Recognition
Use case Name
Document Recognition
Description
The Administrator or End-user trains the system according to the given symbols or
alphabets. Then the characters are recognized after the system is trained.
Actors
Trains System
Recognize characters
Administrator or
end-user

31
Flow of Events
1. The user trains the system to recognize the characters.
2. After the system is trained the characters are recognized.
Pre-Condition
Before trying to recognize the characters, the system should be trained first with the font
characteristics and the font size.
Opens document in Editor
Enters word for search
searches the word
Figure 8:Use-Case Diagram For Document searching
Administrator or
end-user
Use case Name
Document Searching
Description
The Administrator or End-user opens the document in editor. He enters the word which he
is looking for in that document. Then he searches the word.

32
Actors
Flow of Events
1. The user opens the document for searching a word he required.
2. After opening the document he enters the word for search.
3. Finally searches the word in that document.
Pre And Post Conditions
No pre-condition and post-condition

Overall Use-Case Diagram
Document recognition
Figure 9
33
end-user1
end-user2
Document modification Document deletion
scan documents
store documents
Document processing
<<includes>>
<<includes>>
Document processing
Document editing
administrator
Trains the system
end-user

34
4.2.2 CLASS DIAGRAMS
The class diagram is the main building block in object oriented modeling. The classes in a
class diagram represent both the main objects and or interactions in the application and the
objects to be programmed.
 The class diagram of our OCR system consists of 9classes. They are
1. MainScreen
2. Editor
3. HelpFrame
4. Document
5. HEntry
6. Entry
7. TrainingSet
8. KohonenNetwork
9. PrintedFrame.
Among all these classes the MainScreen is the main class that represents all the major
functions carried out by our OCR system. The MainScreen class has an association with
five classes viz., Editor, HelpFrame, Document, TrainingSet, PrintedFrame. And the
TrainingSet class in-turn has an association with the HEntry and the KohonenNetwork
classes. The PrintedFrame has an association with the Entry and KohonenNetwork classes.

Figure 10:Class Diagram
35
4.2.3 SEQUENCE DIAGRAMS
Sequence diagrams are sometimes called Event-trace diagrams, event scenarios, and
timing diagrams. A sequence diagram shows, as parallel vertical lines (lifelines), different
processes or objects that live simultaneously, and, as horizontal arrows, the messages
exchanged between them, in the order in which they occur. This allows the specification of
simple runtime scenarios in a graphical manner.

In sequence diagram, the class objects that are used to describe the interaction between
various classes vary from one function to another function. There are five sequence
diagrams short-listed below for presenting the sequence of actions performed by each of the
five modules. The key class object involved in all of these module functions is MainScreen
class which controls the interaction among various class objects.
Sequence Diagram for Document Processing
36
1. Objects
Administrator - “a”
MainScreen - “m”
Document - “d”
SystemMemory - “s”
2. Links
1. Administrator object to MainScreen object.
2. MainScreen object to Document object.
3. Document object to SystemMemory object.
4. SystemMemory object to Administrator object.
3. Messages
1. Process documents

a:Administraror m:MainSreen d:Document s:SystemMemory
2.Scan documents
37
2. Scan documents
3. Scans
4. Stores documents
5. Stores
6. Returns the processed documents
1.Process documents
3.Scans
4.Stores documents
Figure 11:Sequence Diagram for Processing
5.Stores
6.Returns the processed documents

Sequence Diagram for System Training
38
1. Objects
System - “s”
TrainingSet - “t”
2. Links
1. Administrator object to System object
2. System object to TrainingSet object
3. TrainingSet object to System object
4. System object to Administrator object
3. Messages
1. Specifies the font characters
2. Stores it as an image
3. Trains the system with new font
4. System recognizes new font and returns for user

a:Administrator s:System t:TrainingSet
1.Specifies the font characters
Figure 12:Sequence Diagram for Training
Sequence Diagram for Document Recognition
39
1. Objects
TrainingSet - “t”
2. Links
1. Administrator object to MainScreen object
2. MainScreen object to SystemMemory object
3. SystemMemory object to MainScreen object
4. MainScreen object to TrainingSet object
2.Stores it as an image
3.Trains the system with new font
4.System recognizes new font and returns for user

5. TrainingSet object to MainScreen object
6. MainScreen object to Administrator object
a:Administrator m:MainScreen s:SystemMemory t:TrainingSet
2.Store processed document
3.Read file image
40
3. Messages
1. Recognize documents
2. Store processed document
3. Read file image
4. Recognize using ocr
5. Send processed document
6. Recognize the characters
1:Recognise documents
4.Recognise using ocr
5.Send processed document
6.Recognise the characters
Figure 13:Sequence Diagram for Recognition

Sequence Diagram for Document Editing
41
1. Objects
Document - “d”
2. Links
1. Administrator object to MainScreen object.
2. MainScreen object to Document object.
3. MainScreen object to Document object
5. Document object to SystemMemory object.
6. SystemMemory object to Administrator object.
3. Messages
1. Edit document
2. Adding document
3. Adds
4. Deleting document

a:Administrator m:MainScreen d.Document s:SystemMemory
2.Adding document
4.Deleting content
6.Modifing content
9.Administrator accesses the edited documents
42
5. Deletes
6. Modifying document
7. Modifies
8. Stores the edited documents
9. Administrator accesses the edited documents
1.Edit document
3.adds
5.Deletes
7.Modifies
8.Stores the edited documents
Figure 14:Sequence Diagram for Editing

Sequence Diagram for Document Searching
43
 Objects
Document – “d”
 Links
1. Administrator object to MainScreen object
3. Document object to Administrator object
 Messages
1. Specifies the word
2. Searches the word
3. Searches
4. Returns the location of the word

a:Administrator m:MainScreen d:Document
1.Specifies the word
2.Searches the word
4.Returns the location of the word
Figure 15:Sequence Diagram for Searching
44
4.2.5 ACTIVITY DIAGRAMS
The purpose of activity diagram is to provide a view of flows and what is going on inside a
use case or among several classes. Activity diagram can also be used to represent a class’s
method implementation. A token represents an operation. An activity is shown as a round
box containing the name of the operation. An outgoing solid arrow attached to the end of
activity symbol indicates a transition triggered by the completion.
3.Searches

Activity Diagram For Document Processing
Request document
processing
Process
document
[ scanner not ready ]
[ scanner ready ]
Figure 16:Activity Diagram For Processing
45
Retry for
scanning
Scan
documents
Store
documents

[ Document exists ]
Retrieves
document
Figure 17:Activity Diagram for document Retrieval
46
Request
document
Initiate search
Returns
message
Sends document to
user
[ Document does not exist ]

Activity Diagram For Document Storage
Edit
documents
[ user choses modify ]
Figure 18:Activity Diagram for Document Storage
47
Delete document
content
Add document [ user choses delete ]
content
[ user choses add ]
Modify
document
Store
documents

48
4.2.6 COMPONENT DIAGRAM
The crucial component in our component diagram that plays a major role in implementing
the OCR system is the GUI component. All other components that is Document processing
and recognition, Document editing and Document Searching depends on it. They are as
follows:-
 GUI Component that is used to design GUI screens for interacting with the end-user and
administrator.
 From the GUI component other components functionalities are carried out. The
functionalities include Document processing and recognition, Document editing and
Document Searching.

GUI Document Processing
Figure 19:Component Diagram
49
4.2.7 DEPLOYMENT DIAGRAM
A deployment diagram serves to model the physical deployment of artifacts on
deployment targets. Deployment diagrams show "the allocation of Artifacts to Nodes
according to the Deployments defined between them.”.
and Recognition
Editing
Searching
GUI Screens
adding,deleting,
modifying
scanning,storing
and recognising
characters
supports user
search function

In the deployment diagram of our OCR system, the server role is played by admin called
Librarian. There can be N number of clients who can access the digital library data content
at a time. The clients here may be either the students or the faculty or the both.
 The actions performed by the Administrator are document processing, searching and
editing where as the actions performed by the end-user are only document searching
<<Server>>
<<Client1>> <<Client2>> <<ClientN>>
50
and editing.
Figure 18:Deployment Diagram
Document
searching,
editing
Document
searching,
editing
Document
searching,
editing
Document
Processing,
editing and
searching

5.CODING/CODE TEMPLATES
51
Sample Code
CODE SNIPPETS FOR TRAINING
public class TrainingSet
{
protected int inputCount;
protected int outputCount;
protected double input[][];
protected double output[][];
protected double classify[];
protected int trainingSetCount;
TrainingSet ( int inputCount , int outputCount )
{
this.inputCount = inputCount;s
this.outputCount = outputCount;
trainingSetCount = 0;
}
public int getInputCount()
{
return inputCount;

52
}
public int getOutputCount()
{
return outputCount;
}
public void setTrainingSetCount(int trainingSetCount)
{
this.trainingSetCount = trainingSetCount;
input = new double[trainingSetCount][inputCount];
output = new double[trainingSetCount][outputCount];
classify = new double[trainingSetCount];
}
public int getTrainingSetCount()
{
return trainingSetCount;
}
void setInput(int set,int index,double value) throws RuntimeException
{
if ( (set<0) || (set>=trainingSetCount) )
throw(new RuntimeException("Training set out of range:" + set ));
if ( (index<0) || (index>=inputCount) )
throw(new RuntimeException("Training input index out of range:" + index ));
input[set][index] = value;

53
}
void setOutput(int set,int index,double value)
throws RuntimeException
{
if ( (index<0) || (set>=outputCount) )
output[set][index] = value;
}
void setClassify(int set,double value)
{
classify[set] = value;
}
double getInput(int set,int index)
{
if ( (index<0) || (index>=inputCount) )

54
return input[set][index];
}
double getOutput(int set,int index)
{
if ( (index<0) || (set>=outputCount) )
return output[set][index];
}
double getClassify(int set)
{
return classify[set];
}
void CalculateClass(int c)
{for ( int i=0;i<=trainingSetCount;i++ ) {
classify[i] = c + 0.1;
} }

55
double []getOutputSet(int set)
{if ( (set<0) || (set>=trainingSetCount) )
return output[set];}
double []getInputSet(int set)
{
return input[set];
}
}

6.TESTING
The purpose of testing is to discover errors. Testing is the process of trying to discover
every conceivable fault or weakness in a work product. It provides a way to check the
functionality of components, sub assemblies, assemblies and/or a finished product. It is the
process of exercising software with the intent of ensuring that the software system meets its
requirements and user expectations and does not fail in an unacceptable manner. There are
various types of test. Each test type addresses a specific testing requirement.
56
6.1 TYPES OF TESTS
Unit Testing
Unit testing involves the design of test cases that validate that the internal program logic
is functioning properly, and that program input produces valid outputs. All decision
branches and internal code flow should be validated. It is the testing of individual software
units of the application .it is done after the completion of an individual unit before
integration. This is a structural testing, that relies on knowledge of its construction and is
invasive. Unit tests perform basic tests at component level and test a specific business
process, application, and/or system configuration. Unit tests ensure that each unique path of
a business process performs accurately to the documented specifications and contains
clearly defined inputs and expected results.

57
Integration Testing
Integration tests are designed to test integrated software components to determine if they
actually run as one program. Testing is event driven and is more concerned with the basic
outcome of screens or fields. Integration tests demonstrate that although the components
were individually satisfaction, as shown by successfully unit testing, the combination of
components is correct and consistent. Integration testing is specifically aimed at exposing
the problems that arise from the combination of components.
System Testing
System testing ensures that the entire integrated software system meets requirements. It
tests a configuration to ensure known and predictable results. An example of system testing
is the configuration oriented system integration test. System testing is based on process
descriptions and flows, emphasizing pre-driven process links and integration points.
Functional Testing
Functional tests provide a systematic demonstration that functions tested are available as
specified by the business and technical requirements, system documentation, and user
manuals.
Functional testing is centered on the following items:
Valid Input : identified classes of valid input must be accepted.
Invalid Input : identified classes of invalid input must be rejected.
Functions : identified functions must be exercised.
Output : identified classes of application outputs must be exercised.
Systems/Procedures : interfacing systems or procedures must be invoked.

Organization and preparation of functional tests is focused on requirements, key functions,
or special test cases. In addition, systematic coverage pertaining to identify business process
flows, data fields, predefined processes, and successive processes must be considered for
testing. Before functional testing is complete, additional tests are identified and the
effective value of current tests is determined.
 There are two basic approaches of functional testing:
58
a. Black box or functional testing.
b. White box testing or structural testing.
(a) Black box testing
This method is used when knowledge of the specified function that a product has been
design to perform is known. The concept of black box is used to repress..ent a system hose
inside working’s are not available to inspection. In a black box the test item is eaten as
“Black”, since its logic is unknown is what goes in and what comes out, or the input and
output.
In black box testing, we try various inputs and examine the resulting outputs. The black
box testing can also be used for scenarios based test .In this test we verify whether it is
taking valid input and producing resultant out to user. It is imaginary box testing that hides
internal workings. In our project valid input is image resultant output well structured image
should be received.
(b) White box testing
White box testing is concern with testing implementation of the program. The intent of
structural testing is not to exercise all the inputs or outputs but to exercise the different
programming and data structures used in the program. Thus structure testing aims to

achieve test cases that will force the desire coverage of different structures. Two types of
59
path testing are:
1. Statement testing
2. Branch testing
Statement Testing
The main idea of statement testing coverage is to test every statement in the objects
method by executing it at least once. However, realistically, it is impossible to test program
on every single input, so you never can be sure that a program will not fail on some input.
Branch Testing
The main idea behind branch testing coverage is to perform enough tests to ensure that
every branch alternative has been executed at least once under some test. As in statement
testing coverage, it is unfeasible to fully test any program of considerable size.
6.2 UNIT TESTING
Unit testing is usually conducted as part of a combined code and unit test phase of the
software lifecycle, although it is not uncommon for coding and unit testing to be conducted
as two distinct phases.
Test strategy and approach
Field testing will be performed manually and functional tests will be written in detail.
Test objectives
 All field entries must work properly.
 Pages must be activated from the identified link.
 The entry screen, messages and responses must not be delayed.

60
Features to be tested
 Verify that the entries are of the correct format.
 No duplicate entries should be allowed.
 All links should take the user to the correct page.
6.3 INTEGRATION TESTING
Software integration testing is the incremental integration testing of two or more integrated
software components on a single platform to produce failures caused by interface defects.
The task of the integration test is to check that components or software applications, ex.
components in a software system or one step up software applications at the company level
- interact without error.
Test Results: All the test cases mentioned above passed successfully. No defects
encountered.
6.4 ACCEPTANCE TESTING
User Acceptance Testing is a critical phase of any project and requires significant
participation by the end user. It also ensures that the system meets the functional
requirements.
Test Results: All the test cases mentioned above passed successfully. No defects
encountered.

61
OUTPUT SCREENS
The following shows the series of output screens and how the actual process of
implementing OCR takes place:-
 The first and the home page of our optical character recognition system looks as shown
in figure 8.1.It provides an interface to the user such that the user can access any
module that is present in this software from this page itself. The page is as shown
below:-
Figure 18: Main screen
 There are two types of recognitions in the document recognition module. They are
handwrtitten letter recognition and the scanned document recognition. The
implementation of the handwritten document recognition proceeds as follows:-

 Process Explaining Hand Written Letter Recognition
Firstly, When we click the handwritten recognition button on the home page the
following screen appears on the user interface presenting the user all the operations that
62
can be performed in this module:-
Hand Written Screen 1
 From the above screen we can write letters on the workspace provided with the name
“Draw Letters Here” by using mouse pointer. For recognizing these letters we have to
train the system first. Else, it will give an error message depicting that the system has to
be trained first. This process is explained with the following screens:-
Firstly suppose that we have drawn a letter named ‘A’ in the workspace provided.

Hand written Screen 2
 Now suppose that you have clicked the “Recognize” button without training, for
recognizing the character you have written and showing the recognized character in the
grid. Then it will display an error message as shown below:-
63

Hand written screen 3
 Now if we click the “Begin Training” button before proceeding with the recognition
then a status message with successful status is shown below:-
64

 Since the training has been completed, now the letter ‘A’ can be recognized by clicking
then “Recognize” button. Then the letter ‘A’ will appear in the grid as output. It is as
65
shown below:-
 Once we have provided training to the system for every session, the system do not need
any further training for any kind of letter in any kind of language. That is, once the
training is provided to the system for at-least one character then onwards, it will
recognize any character written in the workspace without the need of training it.
For Example, First we have written letter ‘A’ provided training for it and recognized the
letter A. Now we have written letter S. Now without the need for the training we can
directly recognize the letter ‘S’ in the grid by clicking the “Recognize” button. Thus we
do not need to train the system further.

 Since we have provided the training to the system once with one character of English
language, We can now recognize the characters of any language other than English that
66

too without the need for training. Suppose we have written a telugu character as shown
67
below:-
 Now we can directly recognize the above telugu character without the need of training
the system. Just click the “Recognize” button once after drawing the letter in the
workspace.

 Next other than providing the training to the system through the drawn letters, we can
also train the system by providing the characters through the keyboard and storing them
as patterns. Later we provide training to the system on those patterns.
Firstly, We provide the input through the keyboard as follows:-
68

 If we click ok, those letters will be saved in stored patterns workspace. Later we can
click “Begin Training” button such that those stored patterns will be trained to the
system. Else, it will provide an error message depicting that the system needs training.
 Now suppose that if we write a word ‘sr’ and click “Recognize” button before
providing training on the above stored pattern ‘A’ then an error message will be
displayed depicting that the system needs to be trained on the stored patterns as shown
69
below:-

 Now click the “Begin Training” button before you attempt to recognize the drawn word
‘sr’. Then it produces an output screen as shown below indicating that the training has
70
been completed:-
 Now if we click the “Recognize” button then the drawn word ‘sr’ is recognized and is
shown as an output in the grid format by firing the last neuron in stored patterns.

 Since we have provided training on the stored patterns once, from now onwards we can
just draw the characters or words of any language and we can recognize them directly
by clicking the ”Recognize” button without the need for training the system again. An
71
example is shown for a telugu word.

Hand written Screen 15
 Process Explaining Scanned Document Recognition
Firstly, When we click the “Scanned Document Recognition Button” the main page of
this recognition module is displayed as follows:-
Scanned Screen 1
72

 The data that is present in the first text box is the default image file set by the user. The
user can change the input image file rather than the default image file by clicking open
and then selecting an image file. The procedure is as shown below:-
Scanned Recognition Screen 2
Scanned Recognition Screen3
73

 There are two main tabs under the scanned document recognition. They are training
and recognition. First we should train the system under training module. Only then we
can recognize the characters from the input image provided using the recognition
module. The training tab under scanned document recognition looks like this.
 The above figure shows the default input image for training. We can change the training
input image for different fonts by opening different input image files and then training
them such that the system gets adapted to the new fonts.
74

 The choice of opening image file changes the default input image for training in to a
75
new image as shown below.

 Now the user can select the bounds up to which the system must be trained just by using
click and drag actions of the mouse. Then selected data highlights as follows:-
 After selection of the data, just click the “Train” button. This lets the system to train
itself with the help of the kohonen network and finally displays a dialog box depicting
that the training has been completed successfully.
76

 Once the training of the system is completed, we move on to the recognition phase
where we open a new scanned image file to be converted into editable document as an
input as per our requirement. Now we select that part of the image from which the data
77
has to be extracted. Then it looks like:-

 Next click the “Crop” button such that it finds the bounds of the text that is selected by
the user by composing a red boundary line around the selected text. It is as shown
78
below:-
Scanned recognition Screen 10
 Finally click the “Recognize” button such that it extracts/recognizes the characters from
the image and presents it to the user. But this data is still not editable. Hence when we
click on the “EDIT” button provided at the bottom-center then the document becomes
both editable and searchable. This complete process is explained in the upcoming two
screens. It is as shown below:-

79

 Now from the data available in the above screen shot, we can make any sort of changes
to the document using cut, copy, paste and etc and You can finally save the document in
two formats(word, text) as per our design.
 The search function can be carried out here by clicking the “find” image button at the
bottom-left corner. Then it asks the user to enter the search term. It is as shown below:-
 Now in the above screen shots dialog box, if you click Ok then there are two cases that
happens over here as per our design. They are:-
Case-1:- If the user enter search term resides in the document, then it will display a
dialog box asking the user, “whether he wants to continue the search or not? “.
If the user clicks yes then it will move the cursor to the search term.
If the user clicks no then it will exit the search.
80

Case-2:-If the user enters a search term that does not reside in the document, then it will
direct display a dialog box saying that the searching is finished. It means that the search
81
term is not present in the document.
Thus the user can understand whether the search term is present in the document or
not just after entering the search term itself.
 If we are searching for a term that is already present in the document then the series of
output screens will be as follows:-

 If we are searching for a term that does not reside in the document then the series of
output screens will be as follows:-
82

 If we are using the editor, you can perform the following actions displayed in the
83
screens below:-

7. PLATFORM/TOOLS USED
SOFTWARE REQUIREMENTS SPECIFICATION
 Operating System : Windows-XP
 Programming Language : Core Java
 User Interface : Swings
HARDWARE REQUIREMENTS SPECIFICATION
 Processor : Pentium IV processor or higher
 RAM : Minimum of 512 MB RAM
 Memory : 500 MB or higher
84

8. CONCLUSION AND FUTURE SCOPE
What does the future hold for OCR? Given enough entrepreneurial designers and sufficient
research and development dollars, OCR can become a powerful tool for future data entry
applications. However, the limited availability of funds in a capital-short environment could
restrict the growth of this technology. But, given the proper impetus and encouragement, a
lot of benefits can be provided by the OCR system. They are:-
 The automated entry of data by OCR is one of the most attractive, labor reducing
85
technology
 The recognition of new font characters by the system is very easy and quick.
 We can edit the information of the documents more conveniently and we can reuse the
edited information as and when required.
 The extension to software other than editing and searching is topic for future works.
The Grid infrastructure used in the implementation of Optical Character Recognition
system can be efficiently used to speed up the translation of image based documents into
structured documents that are currently easy to discover, search and process.
FUTURE ENHANCEMENTS
The Optical Character Recognition software can be enhanced in the future in different kinds
of ways such as:
 Training and recognition speeds can be increased greater and greater by making it
more user-friendly.

Many applications exist where it would be desirable to read handwritten entries. Reading
handwriting is a very difficult task considering the diversities that exist in ordinary
penmanship. However, progress is being made
86

9. REFERENCES
Under this references section, we have mentioned various references from which we
collected our problem and several others that supported us to design the solution for our
problem. These references include either books, papers published through some standards
87
and several websites links with URL’s:-
 For the complete reference and understanding of neural networks refer jeff heaton’s
chapter 1 from www.jeffheaton.com
 For the complete reference and understanding of OCR refer jeff heaton’s chapter 7
from www.jeffheaton.com
 The IEEE standard reference paper from which we collected our problem statement
is authorized by Dana Petcu, Silviu Panica, Viorel Negru and Andrei Eckstein of
Computer Science Department who are from West University of Timisoara,
Romania.
 The reference paper is also authorized by Doina Banciu from National Institute for
Research and Development in Informatics, Romania.
 You can refer the IEEE standard paper written by D. Andrews, R. Brown, C.
Caldwell, et al., “A Parallel Architecture for Performing Real Time Multi-Line
Optical Character Recognition”
 You can refer the IEEE standard paper written by H. Goto, “OCRGrid : A Platform
for Distributed and Cooperative OCR Systems”

10.APPENDIX
88
Appendix A: Glossary
TERMS
All the terms and abbreviations in the project are specified clearly. For further
development of project evolved definitions will be specified
ACRONYMS
IEEE: Institute of Electrical and Electronics Engineers
DFD: Data Flow Diagram
UML: Unified Modeling Language
J2EE: Java 2 Enterprise Edition
GUI: Graphical User Interface
OCR: Optical Character Recognition
GOCR: Grid OCR
Appendix B: Analysis Mode
This includes all the pertinent analysis models, such as data flow diagrams, class diagrams,
use case diagrams, interaction diagrams and state-chart diagrams.

Optical Character Recognition System for Document Processing

Recommended

Recommended

More Related Content

What's hot

What's hot (20)

Similar to Optical Character Recognition System for Document Processing

Similar to Optical Character Recognition System for Document Processing (20)

More from Bharat Kalia

More from Bharat Kalia (10)

Recently uploaded

Recently uploaded (20)

Optical Character Recognition System for Document Processing