ABV-Indian Institute of Information Technology
and Management Gwalior
Group 10
Himanshu Pandey 2018IMT-038
Aakar Srivastava 2018IMT-002
Abhay Chaurasiya 2018IMT-005
Prabhat Dwivedi 2018IMT-067
Puneet 2018IMT-074
C Dheena 2018IMT-026
Sanskar Rathore 2018IMT-90
Arsh Pratap 2018IMT-021
Anand Verma 2018IMT-016
Himanshu Chandola 2018IMT-037
Iris Recognition System
INTRODUCTION
In humans and most mammals and birds, the iris (plural: irides or irises) is a thin,
circular structure in the eye, responsible for controlling the diameter and size of the
pupil and thus the amount of light reaching the retina. Eye color is defined by that of
the iris. In optical terms, the pupil is the eye's aperture, while the iris is the diaphragm.
Iris recognition is an automated method of biometric identification that uses mathematical pattern-recognition
techniques on video images of one or both of the irises of an individual's eyes, whose complex patterns are
unique, stable, and can be seen from some distance.
Iris recognition uses video camera technology with subtle near infrared illumination to acquire images of the
detail-rich, intricate structures of the iris which are visible externally. All publicly deployed iris recognition
systems acquire images of an iris while being illuminated by light in the near infrared wavelength band of the
electromagnetic spectrum
The iris of the eye has been described as the ideal part of the
human body for biometric identification for several reasons:
❖ It is an internal organ that is well protected against damage and wear by a highly transparent
and sensitive membrane (the cornea). This distinguishes it from fingerprints.
❖ The iris is mostly flat, and its geometric configuration is only controlled by two complementary
muscles that control the diameter of the pupil. This makes the iris shape far more predictable.
❖ The iris has a fine texture that like fingerprints is determined randomly during embryonic
gestation. This makes it very unique to each person.
❖ It will not modify a lot in the life making iris scanners more reliable.
• Many commercial iris scanners can be easily fooled by a high quality image of an iris or face in place
of the real thing.
• The scanners are often tough to adjust and can become bothersome for multiple people of
different heights to use in succession.
• The accuracy of scanners can be affected by changes in lighting. Iris scanners are significantly more expen
sive than some other forms of biometrics, as well as password and proximity card security systems.
• Iris recognition is very difficult to perform at a distance larger than a few meters and if the person to be
identified is not cooperating by holding the head still and looking into the camera.
• Iris recognition is susceptible to poor image quality, with associated failure to enroll rates.
Research on biometric methods has gained renewed attention in recent years brought on by an increase
in security concerns. The increasing crime rate has influenced people and their governments to take action and
be more proactive in security issues.
This need for security also extends to the need for individuals
to protect their working environments, homes, personal possessions and assets.
Many biometric techniques have been developed and are being improved with the most successful being
applied in everyday law enforcement and security applications. Iris recognition is considered to be the
most powerful technique for security authentication in present context.
As commercial incentives increase, many new technologies for person identification are being developed, each
with its own strengths and weaknesses and a potential niche market.
The term “Biometrics” is derived from the Greek words “bio” and “metrics”.
Automated biometric systems have only become available over the
last few decades, due to the significant advances in the field of
computer and image processing. The history of biometrics
goes back thousands of years.
The ancient Egyptians and the Chinese played a large role in biometrics
history. Today, the focus is on using biometric face recognition,
iris recognition, retina recognition and identifying characteristics to
stop terrorism and improve security measures.
During 1858, the first recorded systematic capture of hand and finger images for identification
purposes was used by Sir William Herschel, Civil Service 6 of India, who recorded a handprint on
the back of a contract for each worker to distinguish employees.
John Daugman developed and patented the first actual algorithms to perform iris recognition,
published the first papers about it and gave the first live demonstrations.
In a 1953 clinical textbook, F.H. Adle wrote: "In fact, the markings of the iris are so distinctive that
it has been proposed to use photographs as a means of identification, instead of fingerprints."
Adler referred to comments by the British ophthalmologist J.H. Doggart, who in 1949 had
written that: "Just as every human being has different fingerprints, so does the minute
architecture of the iris exhibit variations in every subject examined. Its features represent a series
of variable factors whose conceivable permutations and combinations are almost infinite."
In 1892 the Frenchman A. Bertillon had documented nuances in "Tableau de l'iris humain".
Divination of all sorts of things based on iris patterns goes back to ancient Egypt, to Chaldea
in Babylonia, and to ancient Greece, as documented in stone inscriptions,
painted ceramic artefacts, and the writings of Hippocrates.
Later in the 1980s, two American ophthalmologists, L. Flom and Aran Safir managed to patent
Adler's and Doggart's conjecture that the iris could serve as a human identifier, but they had no a
ctual algorithm or implementation to perform it and so their patent remained conjecture.
The core theoretical idea in Daugman's algorithms is that the failure of a test of statistical
independence can be a very strong basis for pattern recognition, if there is sufficiently high
entropy among samples from different classes.
In 1994 he patented this basis for iris recognition and its underlying computer vision algorithms for i
mage processing, feature extraction, and
matching, and published them in a paper. These algorithms became widely licensed by companies.
In the iris segmentation phase, Daugmans’ algorithm is the most frequently cited
algorithm in the iris recognition literature. It assumes that both iris and pupil have a circular
shape, and an integro-differential operator is used to find their contour. The accuracy of
Duagmans’ algorithm is high in the infrared spectrum compared to the visible light
due to the low quality of the image.
The Hough Transform is the most used algorithm in iris segmentation. First, the edges of an
interested region are detected, and then the Circular Hough Transform will determine the
iris circular boundaries.
In the normalization phase, the segmented iris region is normalized in order to obtain a fixed
number of features from the iris, regardless of its spatial resolution.
The iris is mapped from Cartesian coordinates to a fixed pattern representing Polar coordinates,
which is applied to the region located between the pupil radius and iris radius.
The Rubber Sheet model is a well-known algorithm in iris normalization and suggested by many
researchers.
There are many faults in this iris recognition field. These faults require more in depth research. N
ow a days face recognition systems are more widely used instead of iris recognition systems ca
use they have fixed many issues which iris recognition systems have.
-> Iris recognition systems can be fooled easily. As it takes a plain image of an eye, a fake
printed image of an eye could also fool a system into thinking that the eye is real and result in a
security breach if no human presence is maintained during the authentication. This issue has not
been fixed yet and can definitely better results in time.
-> Iris scanners are relatively higher in cost compared to other biometric modalities. As one
of the leading and latest technology of the modern times, the cost of the iris devices are fairly
high.
-> Iris is small in size and can’t be located from a few meters distance. A person needs to be in
close distance with the iris scanning device to be enrolled on the system properly and also to get
a clear image for proper authentication. So, a proper setup is needed for initiating an iris recogni
tion process. Research is being done to find alternative image acquisition techniques for this.
-> In some cases, it is hard to perform an iris scanning due to the presence of reflections. It could
happen in case of eyelashes, lenses, and anything in general that would cause a reflection.
Methods to circumvent such restrictions are also a field of research
-> The constant use of infrared light in this system may cause harm to the iris because it is
constantly being scanned with infrared light. We need to find alternate image processing techniques
which give equally accurate results.
-> The pupils could dilatate due to biological factors yielding inconsistent results due to iris
hinderence. Research is being done to link biological factors to create better algorithms
The design and implementation of a system for automated iris recognition can be
subdivided in to 3 major parts:
1. IMAGE ACQUISITION : To acquire images with sufficient resolution and
sharpness to support recognition.
2. IRIS LOCALIZATION : To segment the iris from the rest of the image.
3. PATTERN MATCHING : The Iris Code derived from this process is compared
with previously generated Iris Code.
-
Step 1: Capturing the image of the eye using a camera.
Step 2: Differentiating the outline of the iris and the sclera and the pupil from the iris.
Step 3: Encoding the image using demodulation (also removes reflections,
intrusion of eye lid lashes, contact lens outline etc.,). Code is 256 bytes.
sclera
iris
pupil
Live Iris code of the iris presented for authentication is compared with iris code stored in the database.
Bit by bit comparison is made between two irises & no of non matching bits & matching bits are found out.
Number of non matching bits are divided by number of bits to obtain Hamming distance.
Hamming distance gives degree of match or unmatch. For two identical iris code, hamming distance is zero,
and for perfectly unmatch hamming distance is one.
Image Acquisition
Using visible light the texture information A bettertexture information is obtained using
obtained is less. The different layers are infrared light. It gives more precise data for
visible while using visible light . comparison.
Iris Localization
The process of obtaining picture of iris only is called localization.
Delimits the iris from the rest of the acquired image
To identify the approximately concentric circular outer boundaries of the iris and the pupil in a photo
of an eye using Algorithms.
Exclude eyelids, eyelashes and pupil also .
The ENTIRE Process
Image acquisition: This is the first step for the entire process in the identification of iris. When a person desired to
be identified by iris recognition system, first take the picture of eye. The camera can be located between three and a
half inches and one meter to capture the image .
Localization: The obtained iris image has to be preprocessed to identify the iris, which is the portion between the p
upil (inner boundary) and the sclera (outer boundary). The first step in iris localization is to detect pupil which is the
black circular part encircled by iris tissues. The center of pupil can be used to detect the outer radius of iris patterns.
Isolation: Now the task is to segregate the iris. The segmentation can be done by using a masking techniques. Ga
ussian Mask is commonly used. The mask is circular one which has the same radius as the iris. It thus passes all
pixels that are contained in the circle which are all the pixels forming the iris.
Normalization . creating a dimensionally consistent
representation of the iris region
Feature Extraction: Both the Gabor Transform and the Haar Wavelet are considered as the Mother Wavelet. Lapla
cian of Gaussian (LoG) is also used for feature extraction in some papers.
Matching: using hamming codes.
Canny Edge Detection Algorithm:
The Canny edge detector is an edge detection operator that uses a multi-stage algorithm to detect a wide
range of edges in images. It was developed by John F. Canny in 1986. Canny also produced a
computational theory of edge detection explaining why the technique works.
Canny Edge Detection Algorithm:
The algorithm runs in 5 separate steps:
1. Smoothing: Blurring of the image to remove noise.
2. Finding gradients: The edges should be marked where the gradients of the image has Large magnitudes
3. Non-maximum suppression: Only local maxima should be marked as edges.
4. Double thresholding: Potential edges are determined by thresholding.
5. Edge tracking by hysteresis: Final edges are determined by suppressing all edges that are not
connected to a very certain (strong) edge.
The circle Hough Transform (CHT) is a basic technique used in Digital Image Processing, for detecting circular objects in
a digital image. The circle Hough Transform (CHT) is a feature extraction technique for detecting circles.
The Algorithm :
=> For each A[a,b,r] = 0;
=> Process the filtering algorithm on image Gaussian Blurring, convert the image to grayscale, make Canny operator, The Canny
operator gives the edges on image.
Vote the all possible circles in accumulator. The local maximum voted circles of Accumulator A gives the
circle Hough space.
=> The maximum voted circle of Accumulator gives the circle.
➢ The uniqueness of iris and the low probability of a false acceptance or false rejection
all contribute to the benefits of using iris recognition technology.
➢ It provides an accurate and secure method of authenticating users on
to company systems .
➢ The technical performance capability of the iris recognition process far surpasses
that of any biometric technology now available and it is the future of highly secure
security system.
➢ As a substitute of carrying bunk of keys or remembering things as passwords, we can use us as living
password, which is called biometric recognition technology. It uses physical characteristics or habits of
any person for identification.
➢ In biometrics we have a number of characteristics which we are using in our recognition technology as
fingerprint, palm print, signature, face, iris recognition, thumb impression and so on but among these
irises recognition is best technology for identification of a person can say that this technology is not
completely developed .Thus iris recognition is an efficient method for identifying persons.
The results reflected show the reliability of iris scanners and the easy development of such algorithms.
Thank you
Insert the title of your subtitle Here
