1.Introduction …………………………………… …………. 2 2.Literature survey…………………………………………. 4 3.Project definition………………………………. ………….6 4. Block diagram………………………………………... ..… 8 5. Algorithm…………………………………………..9 6. Flowchart…………………………………………..10

7. Implementation steps…………………………......11


2 . Biometric products are used for automated recognition of individuals based on their behavioral and biological characteristics. Individuals generally do not want others to have personal information about them unless they decide to reveal it. So it is need to ensure denial of access to classified data by unauthorized persons. Since the persons to be identified should be physically present at the point of identification. furrows. Such that an unauthorized user may be able to break into an account with little effort. such as crypts. freckles. coronas. forged or misplaced: passwords can be forgotten. facial images. Iris recognition biometric products recognize individuals based on their iris images more specifically the distinctive patterns in the irises created by various structures. frills.INTRODUCTIO N In today’s information age it is not difficult to collect data about an individual and use that information to exercise control over the individual. Conventional methods of identification based on possession of ID cards or exclusive knowledge like Social security number or a password are not altogether reliable. ligaments. Biometric system automatically verifies or recognizes the identity of a living person based on physiological or behavioral characteristics. Biometric technology has now become a viable alternative to traditional identification systems because of its tremendous accuracy and speed. data security has become an inevitable feature. ID cards can be almost lost. ridges. In this context. and collarettes. hand geometry. Other common biometric products use fingerprint features. biometric techniques gives high security for the sensitive information stored in mainframes or to avoid fraudulent use of ATMs.

characteristics of handwritten signatures. and Iris Code is constructed. which is fractional measure of the dissimilarity. image preprocessing is performed followed by extracting the iris portion of the eye image which is called Localization.the iris of the eye. With the increasing demand of enhanced security in our daily lives. Experimental image results show that unique codes can be generated for every eye image and Hamming Distance between any two different iris code has maximum value. even between twins or an individual's right and left eyes. The physical characteristics of the iris do not change with age. The iris itself is stable throughout a person's life (approximately from the age of one). voices or some other physical characteristic. Nowadays many automatic security systems based on iris recognition have been deployed worldwide for border control. restricted access Iris recognition is based on the most mathematically unique biometric . Humans have always identified each other by recognizing faces. One key tool in this area is the use of biometrics. Firstly. Now the use of biometric technologies is providing a means to positively identify or authenticate large numbers of people without having to primarily rely on human to human identification. The human iris is absolutely unique. Finally two Iris Codes are compared to find Hamming Distance. and voice recordings to recognize individuals. This project basically aims at designing an iris matching software system. 3 . The extracted iris part is then normalized using daugman’s rubbersheet model. Personal recognition or identification by a witness is also entrenched in our law and commercial structures. reliable personal identification through biometrics is currently an active topic in the literature of pattern recognition.

LITERATURE SURVEY J. Also there is Daugman’s integro-differential operator for locating the circular iris and pupil regions. IEEE trans. 2002.θ) where r is on the interval [0. Since it works with raw derivative information. Also. and the arcs of the upper and lower eyelids. Wavelet encoding can be used to decompose the data in the iris region into components that appear at different resolutions. present in an image. 1. it does not suffer from the thresholding problems of the Hough transform. it is not mentioned by Boles. and is relative to the comparing iris region. The 4 . “How iris recognition works”. Hence we go ahead with Hough transform for implementing Localization.2π] . The homogenous rubber sheet model devised by Daugman remaps each point within the iris region to a pair of polar coordinates (r. Daugman. however scaling is at match time. how rotational invariance is obtained. since it works only on a local scale. which geometrically warps a newly acquired image into alignment with a selected database image . The integro-differential can be seen as a variation of the Hough transform. since it too makes use of first derivatives of the image and performs a search to find geometric parameters. However. the algorithm can fail where there is noise in the eye image. The Hough transform is a standard computer vision algorithm that can be used to determine the parameters of simple geometric objects. such as from reflections.1] and θ is angle [0. Virtual circles is same as Daugman’s rubber sheet model. rather than scaling to some constant dimensions.Proceedings of 2002 International Conference on Image Processing.Image registration is another technique. The extracted iris portion can be brought to the standard format for comparison by Daugman’s rubber sheet model in our implementation. Vol. such as lines and circles.

Gabor filter is constructed by modulating a sine/cosine wave with a Gaussian which provides localization in space. 1148-1161. 94(11). J. The Hamming distance gives a measure of how many bits are the same between two bit patterns.output of applying the wavelets is then encoded in order to provide a compact and discriminating representation of the iris pattern Daugman. though with loss of localization in frequency. pp 19271935. Daugman J (2006) "Probing the uniqueness and randomness of IrisCodes: Results from 200 billion iris pair comparisons. zero DC components can be obtained for any bandwidth by using a Gabor filter which is Gaussian on a logarithmic scale. However." IEEE Transactions on Pattern Analysis and Machine Intelligence." Proceedings of the IEEE. a decision can be made as to whether the two patterns were generated from different irises or from the same one. Using the Hamming distance of two bit patterns. We will use hamming distance. The weighted Euclidean distance (WED) can be used to compare two templates. (1993) "High confidence visual recognition of persons by a test of statistical independence. vol. pp. 5 . Gabor filter is used in our implementation. this is known as the Log-Gabor filter. The weighting Euclidean distance gives a measure of how similar a collection of values are between two templates. especially if the template is composed of integer values. . A disadvantage of the Gabor filter is that the even symmetric filter will have a DC component whenever the bandwidth is larger than one octave. 15(11).

In order to overcome the security problems biometric system such as Iris Recognition system is most to save memory and time. which uses Iris Recognition Technique using Mat-Lab software 3.2 Objective Security system is designed such that it can be used in public or private places for visitor identification at Airports and offices etc. Matlab is a powerful tool when it comes to mathematical operations but it uses lots of vectors and matrix and these vectors and matrices uses too much memory. reliable and efficient way to recognize and distinguish the people.3 Scope Future development of the software is quite or Visual Basic. 3. Thus implementing our project by C#.1 Aim Design an airport security system. and in fact it is very helpful in improving its efficiency and flexibility in use.PROJECT DEFINITION 3. Its main aim is to nab the terrorist/criminals and identify important personalities during security checking at the airport. whose iris code is present in the database. Also program will work independent from the Matlab. 6 . hard disk and slow down the processing unit of the computer.

Voice. Iris recognition is more accurate. London-Heathrow Airport. Hence iris recognition is popularly used in many applications. ATM.5 How it is different? Fig 3. 3.6 Relevance It is relevantly used at the Airports as a part of security check routine in many western countries like the UAE. It is used during immigration and at the borders where instead of identity cards Iris is used to ascertain the identity of the person. It can replace passwords at banks. Military. Retina. Fingerprint.3.1 Iris accuracy graph Accuracy is the parameter which differentiates Iris recognition technology from rest of the Biometric techniques such as Face. Signature etc. 7 . stable and scalable.

1 Block diagram of iris recognition 8 .BLOCK DIAGRAM 4.1 Block diagram Fig 4.

4. 8. Capture the eye image. Generate iris code. Display the result. 6. 7. 5. 2. Get the extracted portion to standard form by Normalization. Compare the generated code with the code in database. Stop.ALGORITHM 1. 3. Start. Extract the iris portion by Localization. 9 .

10 .


5.4 Flowchart IMPLEMENTATION STEPS 4.1 Acquisition 12 .Fig 4.

Finally. The typical distance from camera to user is about one meter. that is adequate intensity of source constrained by operators comfort with brightness.Fig 4. There are 2 important requisites for this process i) It is desirable to acquire images of the iris with sufficient resolution and Sharpness to support recognition ii) It is important to have good contrast in the interior iris pattern without restoring to a level of illumination that annoys the Operator. the quality metric should be able to predict performance.5. with user cooperation (i. this project should provide insight on which factors negatively impact performance when using traditional iris recognition systems. fixed position with user looking into camera).. we use infrared light images. The primary goal of this project is to design a fully automated image quality block that is capable of discriminating between good and poor quality images. So for improving the performance iris recognition System. Moreover.e.1 Image capture setup The acquisition stage. 13 . captures the iris image in near infrared light ranging from 700-900nm.

comfortable for the measured person as well as robust against natural modifications of the eyes. deformation (e. 4. This involves first employing canny edge detection to generate an 14 . pupil dialation) and possible camera and light differences like shading or noise. Hence. present in an image. sclera. These algorithms are employed in order to extract the iris portion.g.5. all images are captured from proper distance and captured in light illumination. In CASIA databases. we will require infrared light illuminated database. i) Hough Transform The Hough transform is a standard computer vision algorithm that can be used to determine the parameters of simple geometric objects.2 Localization Localization represents the process of segmenting the pupil. scaling. Linear hough transform is an algorithm used to detect the upper and lower eyelids. Pupil and iris detection/segmentation in a traditional system is carried out by using an Hough transform that acts as a circular edge detector. and eyelid regions. such as lines and circles. Also we make use of Thresholding to detect the eyelashes. The procedure of filming human irises must meet some general requirements to be applicable in real scenarios: The process of measurement should be fast. used reflections. The general purpose is a high confidence and real time recognition of an individual’s identity by mathematical analysis of the random patterns that are scanned from the iris of an eye from some distance.Requirements for Iris camera: For more recognition rate. The circular Hough transform can be employed to deduce the radius and centre coordinates of the pupil and iris regions It is decided to use circular Hough transform for detecting the iris and pupil boundaries.

which allowed for weighting of the gradients. since analysis reveals that eyelashes are quite dark when compared with the rest of the eye image. For isolating eyelashes in the CASIA database a simple thresholding technique was used.5. Daugman’s transforms the coordinate system from Cartesian coordinates to a doubly dimensionless nonconcentric polar 15 . 4. A second horizontal line is then drawn. A modified version of Kovesi’s canny edge detection MATLAB® function can be implemented. and interior to the iris region. then no line is fitted. Vertical and horizontal gradients were weighted equally for the inner iris/pupil boundary. and only horizontal gradient information is taken. Eyelids were isolated by first fitting a line to the upper and lower eyelid using the linear Hough transform. which is a form of the Hough transform. the lines are restricted to lie exterior to the pupil region.3 Normalization Normalization is carried out to represent the segmented iris region with regard to invariance of size. Gradients were biased in the vertical direction for the outer iris/sclera boundary. which intersects with the first line at the iris edge that is closest to the pupil. position and orientation. Also. If the maximum in Hough space is lower than a set threshold. The linear Hough transform is implemented using the MATLAB® Radon transform. The second horizontal line allows maximum isolation of eyelid regions. This process and is done for both the top and bottom eyelids. Canny edge detection is used to create an edge map.edge map. since this corresponds to non-occluding eyelids.

3 Daugman’s Rubber Sheet Model For normalization of iris regions a technique based on Daugman’s rubber sheet model was employed.5. Decomposition of a signal is accomplished using a quadrature pair of Gabor filters.we can illustrates the normalization process. The real and imaginary filters are also known as the even symmetric and odd symmetric components respectively.coordinate system. and radial vectors pass through the iris region. Modulation of the sine with a Gaussian provides localization in space. The number of radial lines going around the iris region is defined as the angular resolution. Θ represents the angle (between 0 and 360) and r represents radial resolution Fig 4. (between 0 and 1).4 Feature Encoding A Gabor filter is constructed by modulating a sine/cosine wave with a Gaussian. with a real part specified by a cosine modulated by a Gaussian.5. From Fig . A number of data points are selected along each radial line and this is defined as the radial resolution. and an imaginary part specified by a sine modulated by a Gaussian. 16 . 4. though with loss of localization in frequency. The centre of the pupil was considered as the reference point.

and marks bits in the template as corrupt. since bit-wise comparisons were necessary. so that only significant bits are used in calculating the Hamming distance between two iris templates. since maximum independence occurs in the angular direction. so that when going from one quadrant to another. The rows of the 2D normalized pattern are taken as the 1D signal. only those bits in the iris pattern that corresponds to ‘0’ bits in noise masks of both iris patterns will be used in the calculation. The Hamming distance will be calculated using only the bits generated from the true iris region. The Hamming distance algorithm employed also incorporates noise masking. The encoding process produces a bitwise template containing a number of bits of information. each row corresponds to a circular ring on the iris region. 4.5 Matching For matching. and then these 1D signals are convolved with 1D Gabor wavelets. The output of phase quantization is chosen to be a grey code.5. which corresponds to columns of the normalized pattern. The angular direction is taken rather than the radial one. The output of filtering is then phase quantized to four levels using the Daugman method with each filter producing two bits of data for each phasor. the Hamming distance was chosen as a metric for recognition. Now when taking the Hamming distance. and this modified Hamming distance formula is given as 17 . This will minimize the number of bits disagreeing. if say two intra-class patterns are slightly misaligned and thus will provide more accurate recognition.Feature encoding is implemented by convolving the normalized iris pattern with 1D Gabor wavelets. only 1 bit changes. The 2D normalized pattern is broken up into a number of 1D signals. and a corresponding noise mask which corresponds to corrupt areas within the iris pattern.

This method is suggested by Daugman and corrects for misalignments in the normalized iris pattern caused by rotational differences during imaging. and one shift is defined as one shift to the left.0. and also there will be some noise that goes undetected. since this corresponds to the best match between two templates.6 Decision 18 .where Xj and Yj are the two bit-wise templates to compare. The actual number of shifts required to normalize rotational inconsistencies will be determined by the maximum angle difference between two images of the same eye. 4. Xnj and Ynj are the corresponding noise masks for Xj and Yj. two iris templates generated from the same iris will have a Hamming distance of 0.5. The number of bits moved during each shift is given by two times the number of filters used. and N is the number of bits represented by each template. Normalization is not perfect. followed by one shift to the right. Although. in practice this will not occur. since each filter will generate two bits of information from one pixel of the normalized region. In order to account for rotational inconsistencies. one template is shifted left and right bitwise and a number of Hamming distance values are calculated from successive shift. when the Hamming distance of two templates is calculated. From the calculated Hamming distance values. only the lowest is taken. in theory. so some variation will be present when comparing two intra-class iris templates.

4.On the basis of similarity of two different persons hamming distances. we can take decision that enrolled user is genuine person or imposter and in other words. we can give access to enrolled user or reject its authentication.6 Platform i) Digital Image Processing.7 Language Matlab 19 . 4.