Sei sulla pagina 1di 7

Acknowledgments:

I would like to express my deepest gratitude and thanks to my supervisor, muazzam maqsood, who

suggested the idea of the An Efficient Optical Character Recognition For urdu script and who gave me
the needed information to

start working on the project. Also, I would like to thank him for being supportive and for his guidance

through this semester and for giving me the necessary advices to be able to realize this project. I am

really grateful to his contribution. Moreover, I would like to thank him for his supervising

methodology that made my tasks easier and motivated me through this period.
Table of Content :

1 Abstract

2. Introduction

2.1. Objectives

2.2 Problems with existing system

2.3 Proposed system

3. Requirements

3.1. Functional requirements

3.2 Non Functional requirements

4 System descriptions

5 Conceptual diagrams

5.1 Use case diagram

5.2 Activity diagram

5.3 Sequence diagram


Abstract:
The main aim of the project is to develop OCR software scanned images of machine or handwritten text,
into computer process able format. The offline characters are performing after the printing or writing
has been completed. In online characters recognition computer recognizes the characters as they are
drawn. Within each part, the works are analyzed par rapport a typical OCR pipeline with an emphasis on
the preprocessing, segmentation, feature extraction, classification, and recognition.

Introduction:
Urdu is the national language of Pakistan, and is understood by well over 300 million people around the
world. There is a need to convert historical database of Urdu literature into electronic form, so that
Urdu can prosper in the age of computers. Urdu text recognition endeavors to convert scanned Urdu
documents automatically into computerized text files.

Objectives
 To develop an efficient OCR system for URDU

 To develop an efficient classification technique for URDU OCR

 To develop post-processing algorithms for output generation and error correction of Urdu OCR
Existing systems
Optical Character Recognition (OCR) still remains a challenging task in image processing and machine
learning. There is little work on urdu as compare to other many languages. The accuracy of the existing
systems is not very high.

Proposed system
In proposed system we will develop the OCR that should improve the accuracy rate of the existing
system We will develop algorithm that reduce the working of manual system and convert the desired
image in soft form .The desired output can be used in word document file.

Requirements
As aforementioned, we need to retrieve text from scanned documents or any text

image and make it editable to reuse it and read it word by word. For instance, there are plenty

of books that are only available on printed format, so even if we scan them, they will be

Stored only as images. With the use of the Optical Character Recognition (OCR), these scanned

Documents will be available for later editing and can be reused by the user.

Functional Requirements
The system will perform the following functionality

 System takes the image from the datasets


 scan the image
 recognize the characters in image
 System gives the output in desired result
 System Choose the image from the datasets
Description:
The most important thing is selection of image form the datasets. The user can take a picture of a text
image by camera or choose one from the computer’s folder.

 scan the image


The second step is that the system scan the image with proposed methodology.

 recognize the characters in image


Description:
The characters will be recognized from the image taken by the laptop's camera or from any
Chosen image from datasets. The text will be recognized and ready to be used. Recognition of
the text from the image. Ready to be used.

 System gives the output in desired result


Description:
After recognition of the character System produce the output in desired result. The desired
result can be used in word document file.

Non Functional Requirements


After the functional requirements I have been able to classify the

Non-functional requirements as follows:

Product Requirements:
 Usability Requirements:

The system shall be user friendly and doesn't require any guidance to be used. In

Other words, the system has to be as simple as possible, so its users shall use it

easily.
Reliability Requirements:
The system should not have any unexpected failure. In order to avoid any failure's

Occurrence, the specifications have been respected and followed correctly. The only

problem that may occur in some cases is that the system do not get 100% of the

Characters in the picture.

Efficiency Requirements:
Performance:

The system response time shall be adequate and sufficient enough, that's

why the time required for this system to response to its user's actions has Been managed and
controlled…

Potrebbero piacerti anche