Scribd
Upload
2 views

Irish Segmentation Repot.word

The Irish Segmentation Report provides a detailed analysis of the Irish market by segmenting consumers based on various demographic, psychographic, and behavioral factors. It outlines key characteristics of different market segments, such as age, income, lifestyle, values, shopping habits, and preferences. The report typically includes insights on market trends, consumer needs, and potential opportunities for businesses targeting specific segments. It may also offer recommendations for tailored

Uploaded by

Nikhil Halle
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
2 views

Irish Segmentation Repot.word

The Irish Segmentation Report provides a detailed analysis of the Irish market by segmenting consumers based on various demographic, psychographic, and behavioral factors. It outlines key characteristics of different market segments, such as age, income, lifestyle, values, shopping habits, and preferences. The report typically includes insights on market trends, consumer needs, and potential opportunities for businesses targeting specific segments. It may also offer recommendations for tailored

Uploaded by

Nikhil Halle
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 35

LOCALIZATION AND SEGMENTATION OF NON-IDEAL IRIS IMAGES

Prepared By
AYUSH NARAYAN SHUKLA (15101104019)
RITHIK BANERJEE (15101104063)
ANIKET PATRA (15101104016)

Under the Guidance of


Prof. CHINMOY GHOSH
Assistant Professor
Department of Computer Science & Engineering
Jalpaiguri Govt. Engineering College (Autonomous)

PROJECT REPORT
Submitted in partial fulfillment of the requirement for the degree of
Bachelor of Technology

Department of Computer Science & Engineering


Jalpaiguri Govt. Engineering College (Autonomous)

Affiliated to

Maulana Abul Kalam Azad University of Technology, West Bengal


May 2019
Jalpaiguri Govt. Engineering College (Autonomous)

I
CERTIFICATION

Jalpaiguri Govt. Engineering College


Faculty of Computer Science & Engineering

This is to certify that the work in preparing the project entitled


Localization & Segmentation of Non-Ideal Iris Images", has been
carried out by Ayush Narayan Shukla,Rithik Banerjee and Aniket
Patra under my guidance during the session 2018-19 and accepted
in partial fulfillment of requirement for the degree of Bachelor of
Technology in Computer Science & Engineering.

II
Acknowledgement

We sincerely thank our project mentor Prof. Chinmoy Ghosh for guiding and giving us
his valuable time and advice. He always enriched us with his knowledge and gave us the
necessary input to carry out this work. We are grateful to him for his extra efforts and for
being patient with us. We are grateful to Prof. Dhiman Mondal, Head of the Department
of Computer Science & Engineering for permitting us to make use of the facilities available
in the department to carry out the project successfully. Last but not the least we express our
sincere thanks to all of our other staffs and our parents who have patiently extended all
sorts of help for accomplishing this undertaking.

III
Abstract

Biometric deals with Identification of individuals based on their biological or


behavioural characteristics. Iris recognition system is regarded as the most reliable and
accurate biometric identification system available. Traditional personal authentication
methods have many instinctive defects. Biometrics is an effective technology to overcome
these defects. Among the available biometric approaches, iris recognition is one of the most
accurate techniques. In this project work, two approaches for Iris recognition system have
been proposed. Simple morphological operations and two dimensional median filtering
techniques are used to detect the pupil using OpenCV python. The noises such as eyelashes,
reflections are removed through the linear thresholding. Finally after the circle is detected
around the iris it is cropped using a 8 unit mask so that it could be used for feature
extraction process.
Iris recognition is an automated method of biometric identification that uses
mathematical pattern-recognition techniques on video images of the irises of an individual's
eyes, whose complex random patterns are unique and can be seen from some distance. It
has a very high accuracy (infinitesimally small false match rates) and is non-destructive as
compared to retina-scanning. Hence, it finds a great usage in security systems today and in
future.

IV
Index

Chapter 1
Introduction 1
1.1 Problem Statement 3
1.2 Problem Description 3
1.3 Tools and platforms 4
Chapter 2
Literature Survey 5
Chapter 3
Concept and Problem analysis 7
7
3.2 Image 8
Chapter 4
Methodology 16
4.1 Databases 16
4.2 Image Pre-processing 16
4.3 Localization 19
4.4 Segmentation 20
Chapter 5
Sample Code 22
Chapter 6
Output Images 24
Chapter 7
Conclusion and Future Scopes 26
References 27

V
List of Figures

1.1: A front view of the Human Iris [3] 1


1.2: The Iris Recognition stages 2
1.3: Examples of Non ideal Images 3
3.1: Morphological Operations: (a)Erosion, (b)Dilation, (c)Opening and,(d)
Closing 11
3.2: CED Steps 13
3.3: Grab-cut Algorithm 15
4.1: Input Image 17
4.2: Grab-cut 17
4.3: Black Hat 18
19
19
4.6: Localized Image 20
4.7: Segmented Image 21
6: Output Images 24

VI
Lists of Tables

3.1: Comparisons of Different Biometric Technique 7


4.1: UBIRIS .v2 16

VII

You might also like