A Presentation of Project Synopsis of B

8/3/2019 A Presentation of Project Synopsis of B

1/19

APRESENTATION

OFPROJECTSYNOPSISOFB.E. 7TH SEMESTER

Under the guidance of :Asst.Prof.Anish Lazrus

Presented by-

S Vijaylaxmi

Shripritha Gupta

Jagrati Shrivastava

5/2/2012 5:01 PM

1


2/19

OUTLINE OF PRESENTATION Objective

Motivation

Challenges

Hardware and software requirements

Introduction

Proposed methodology

Flow diagram

Input digit image

Pre process

Feature extraction

Multi feature classification

Expected outcome

Future scope

References

5/2/201

25:01PM

2


3/19

OBJECTIVE

This is an digit recognition application. We draw a

digit in the picture box and the module recognizesthe digit and displays the result.

5/2/201

25:01PM

3


4/19

MOTIVATION

Digit recognition module finds itself applied in thefollowing areas:

o ZIP code recognition.

o Lottery ticket recognition.

o

Cards used for e-payment.

5/2/201

25:01PM

4


5/19

CHALLENGES

Every individual has his/her unique handwriting.

No imaging system has 100% recognition accuracy.

Actual performance dependent on environment.

5/2/201

25:01PM

5


6/19

HARDWARE & SOFTWAREREQUIREMENTS

HARDWARE:

256 MB RAM.

Windows 2000/XP.

Intel N atom processor.

SOFTWARE:

o VB.NET.

o Database used: notepad.

5/2/201

25:01PM

6


7/19

INTRODUCTION

This is an digit recognition application. First wedraw a digit in the picture box. Then the imageprocessing begins and recognize the digit and

returns the result. Database includes handwrittendigits which are collected from many people. Thesedigit images converted to binary type before addedto the database.

5/2/20125:01PM

7


8/19

PAPER-01:

Rafael M. O. Cruz, George D. C. Cavalcanti and Tsang IngRenCenter of Informatics, Federal University ofPernambuco Recife, Brazil

It is herein proposed a handwritten digit recognition systemwhich uses multiple feature extraction methods and classifierensemble. The combination of the feature extraction methodsis motivated by the observation that different feature extractionalgorithms have a better discriminative power for some typesof digits.

5/2/20125:01PM

8


9/19

PROPOSED METHODOLOGY

Some of the misclassified digits are ambiguouseither by segmentation problems, peculiar writingstyle or distortions. A strategy to reject thisambiguous digits and improvements to recognize

the misclassified digits that can be easilyrecognized by humans are being studied.

Our approach is based on the following block

diagram.

5/2/20125:01PM

9


10/19

PROPOSED FLOWDIAGRAMOFOURWORK

Input digitimage Pre process

Featureextraction

Multi featureclassification

5/2/20125:01PM

10


11/19

INPUT DIGIT IMAGE

We have used a Bitmap function which allows theuser to input a handwritten digit.

5/2/20125:01PM

11


12/19

PRE-PROCESS

Digit is written with black digital ink.

It searches from left to right for black pixels startingfrom left top corner of the area specified for writing. Atrace of a black pixel is the indication of the presence

of a character.

The continuous absence of black pixels black couldbe a gap between two rows. To make sure whether it

is a gap, algorithm searches from left to right againstevery white pixel, if there is no trace of white pixel forthe entire row, the gap is confirmed.

5/2/20125:01PM

12


13/19

(a) threshold original (b) thinned (with spurs) (c) Pruned (by 5 pixels)

The digit images are thinned to a thickness of one pixel.

This can lead undesired side-effects ,such as spurs.

oTHINNING5/2/20125:01PM

13


14/19

FEATURE EXTRACTION

In the feature extraction module, two feature setsare extracted from each digit image:

1. Numbers of ending point, bifurcation, crossand their location,

2. Number of closed curve.

Numberof Endingpoint

0 1 2 3 4 >=5

Possibledigits

0 8 6 9 1 2 34 5 7

2 3 45

4 rejected

5/2/20125:01PM

14


15/19

MULTI FEATURE CLASSIFICATION

In this phase multi-features such as orientationinformation, likeness degree are considered torecognize the digit.

The digit which has the highest percentage ofsimilarity is taken as the final recognized digit.

5/2/20125:01PM

15


16/19

EXPECTED OUTCOMES

The main goal is purely educational one, amoderate recognition rate of 95% is expected.

We will try to recognize handwritten digits ofdifferent people.

5/2/20125:01PM

16


17/19

FUTURE SCOPE

Future work will focus on better selection of multi-features and improve the system performance.

Multiple digits can be recognized simultaneously.

5/2/20125:01PM

17


18/19

REFERENCES

Lottery Digit Recognition Based on Multi-features-Decong Yu, Lihong Ma, Member, IEEE andHanqing Lu, Senior Member, IEEE.

On-line Handwritten Character Recognition-Muhammad Faisal Zafar, Dzulkifli Mohamad, andRazib M. Othman

Handwritten Digit Recognition Using Multipl FeatureExtraction Techniques and Classifier Ensemble-Rafael M. O. Cruz, George D. C. Cavalcanti andTsang Ing Ren Center of Informatics, FederalUniversity of Pernambuco

5/2/20125:01PM

18


19/19

Thank YouAny Suggestion please

5/2/20125:01PM

19

A Presentation of Project Synopsis of B

Documents