Circular Hough Transform for Iris localization

This article presents a robust method for detecting iris features in frontal face images based on circular Hough transform. The software of the application is based on detecting the circles surrounding the exterior iris pattern from a set of facial images in different color spaces. The circular Hough transform is used for this purpose. First an edge detection technique is used for finding the edges in the input image. After that the characteristic points of circles are determined, after which the pattern of the iris is extracted. Good results are obtained in different color spaces.


Introduction
Identificat ion of people is getting more and more importance in the increasing network society [1]. Bio metrics is the branch of science in which human beings are identified with their behavioral or physical characteristics. Physical characteristics include face, finger, iris, ret ina, hand geometry; palm p rint etc. where as behavioral characteristics include signature, gait, voice…etc. In all of these characteristics, iris recognition is gain ing mo re attention because the iris of every person is unique and it never changes during a person's lifetime [2].
Generalized iris recognition consists of image acquisition, iris segmentation and localization (preprocessing), feature extraction and feature comparison (matching). Bio metric based personal identificat ion using iris requires accurate iris localization fro m an eye image [3].
Several researchers have imp lemented various methods for segmentation and localising the iris. John Daugman [5] has proposed one of the most practical and robust methodologies, constituting the basis of many functioning systems. He used integro-differential operator to find both the iris inner and outer boundaries for iris segmentation. Wildes [4] proposed a gradient based binary edge map construction followed by circular Hough transform fo r iris segmentation [2].
Almost all methods stated are based on the assumptions that cent re of iris (Out er Boundary) and Pup il (Inner boundary) is same and iris is perfect ly circular in shapes, which are practically incorrect. Therefore, the iris segmentation and localization fro m an acquired image leads to the loss of texture data near to pupil and/or outer iris boundary.
The effect is more serious when the iris is occluded [2].
In recent years, various methods of iris detection for gaze detection, applied to man-mach ine interfaces have been proposed [1,2,3,4]. However, most studies did not report the relat ionship between the accuracy rate of the iris detection and the directions of the face and the eyes. Actually, the shape of facial parts is not only different depending on the person, but also dynamically changes depending on the movement o f the head, facial exp ressions, and so on. Also, when a person faces down, the eye regions tend to be dark. In this case, it is difficult to detect iris in the face. However, most studies are based on research of the eye region to detect iris. Where, these methods extract the eye regions before detecting irises.
An authentication system for iris recognition is reputed to be the most accurate among all b io metric methods because of its acceptance, reliab ility and accuracy. Ophthalmologists originally proposed that the iris of the eye might be used as a kind of optical fingerprint for personal identification. Their proposal was based on clinical results that every iris is unique and it remains almost unchanged in clinical photographs. The human iris begins to form during the third month of gestation and is comp lete by the eighth month, though pigmentation continues into the first year after birth. It has been discovered that every iris is unique since two people (even two identical twins) have uncorrelated iris patterns [5], and yet stable throughout the human life. It is suggested in recent years that the human irises might be as distinct as fingerprint for different indiv iduals, leading to the idea that iris patterns may be used as unique identification features [11].
Research in the area of iris recognition has been receiving considerable attention and a number of techniques and algorithms have been proposed over the last few years.
A number of algorith ms have been developed for iris localization. One of them is based on the Hough transform. An iris segmentation algorithm based on the circular Hough transform is applied in [6,7,8]. At first, the canny edge detection algorithm is applied. The eye image is represented using edges by applying two thresholds to bring out the transition fro m pupil to iris and fro m iris to sclera. Then circular Hough transform is applied to detect the inner and outer boundaries of the iris. The circular Hough transform is emp loyed to deduce the radius and centre coordinates of the pupil and iris regions. In this operation, the radius intervals are defined for inner and outer circles. Starting fro m the upper left corner of iris the circu lar Hough transform is applied. This algorith m is used for each inner and outer circle separately. The votes are calculated in the Hough space for the parameters of circles passing through each edge point. Here some circle parameters may be found. The parameters that have maximu m value are corresponded to the centre coordinates [6].
After determining centre coordinates, the radius r of the inner circle is determined. The same procedure is applied for the outer circle to determine its centre coordinates and radius. Using determined inner and outer radiuses the iris region is detected. The application of the Hough transform needs long time to locate the boundaries of the iris [6].
The aim of this work is to realize an application wh ich detects the iris pattern fro m an eye image. The software of the application is based on detecting the circles surrounding the exterior iris pattern. Figure 1 shows an overview of the proposed method. Our work concerns the iris detection by the geometric model "Hough transform" using the facial images of the "Fei-Fei Li" database [9], 396 images of different subjects with 24 frames per individual are used.
The paper is presented as follows: section 2 presents the state of the art for iris localizat ion and recognition; Section 3 describes the circular Hough transform for known and unknown radius. Section 4 presents the algorith m applied for iris detection; results obtained for facial images are presented in section 5. Conclusion is drawn in section 5.

State of the art for Iris Localization
Methods such as the Integro-differential, Hough transfor m and active contour models are well known techniques in use for iris localisation. These methods are described below including their strengths and weaknesses [11].

Daug man_s Integro-Differenti al Operator
In order to localise an iris, Daug man proposed an Integro-differential operator method. It assumes that the pupil and limbus are circu lar contours and operate as a circular edge detector. Detecting the upper and lower eyelids is also carried out using the Integro-differential operator by adjusting the contour search fro m circu lar to a designed arcuate shape [11].The Integro-d ifferential operato r is defined as follo ws: The operator pixel-wise searches throughout the raw input image, I(x,y), and obtains the blurred partial derivative of the integral over normalised circu lar contours in different radii. The pupil and limbus boundaries are expected to maximize the contour integral derivative, where the intensity values over the circular borders would make a sudden change.
is a smoothing function controlled by σ that smoothes the image intensity for a mo re precise search [11].
This method can result in false detection due to noise such as strong boundaries of upper and lower eyelids since it works only on a local scale.

Hough Transform
The Hough Transform is an algorith m p resented by Paul Hough in 1962 for the detection of features of a part icular shape like lines or circles in dig italized images [18].
The classic Hough Transform is a standard algorithm for line and circle detection. It can be applied to many computer vision problems as most images contain feature boundaries which can be described by regular curves. The main advantage of the Hough transform technique is that it is tolerant to gaps in feature boundary descriptions and is relatively unaffected by image noise, unlike edge detectors [17]. Hough transform is a standard image analysis tool for finding curves that can be defined in a parametrical form such as lines and circles. The circular Hough transform can be employed to deduce the radius and centre coordinates of the pupil and iris regions [11].
Wildes [12], Kong and Zhang [13], Tisse et al. [14] and Ma et al. [15] have all used Hough transform to localize irises. The localizat ion method, similar to Daug man's method, is also based on the first derivative of the image intensity. In the method proposed by Wildes, an edge map of the image is first obtained by thresholding the magnitude of the image intensity gradient: [11]. Where: G(x,y) is a Gaussian smoothing function with scaling parameter σ selecting the proper scale of edge analysis. The edge map is then used in a voting process to maximise the defined Hough transform for the desired contour. A maximu m point in the Hough space will correspond to the radius r and centre coordinates x c and y c of the circle best defined by the edge points according to equation: Wildes et al. and Kong and Zhang also make use of the parabolic Hough transform to detect the eyelids by approximating the upper and lower eyelids with parabolic arcs [11].
The Hough transform method requires the threshold values to be chosen for edge detection, and this may result in critical edge points being removed, thus resulting in failures to detect circles/arcs. In addition, Hough transform is computationally intensive due to its "brute-force" approach, and thus may not be suitable for real time applications [11].

Discrete Circular Acti ve Contours
Ritter proposed an active contour model to localise iris in an image. The model detects pupil and limbus by activating and controlling the selected active contour using two defined forces: internal and external [11].
The internal forces are designed to expand the contour and keep it circular. Th is force model assumes that pupil and limbus are globally circular, rather than locally, to minimise the undesired deformat ions due to peculiar reflections and dark patches near the pupil boundary. The contour detection process of the model is based on the equilibriu m of the defined internal forces with the external forces. The external forces are obtained from the grey level intensity values of the image and are designed to push the vertices inward. The movement of the contour is based on the composition of the internal and external forces over the contour vertices. Each vertex is moved between time t and (t+1) by Where F int,i is the internal force, F e xt,i is the external force and V i is the position of vertex i.
A point interior to the pupil is located fro m a variance image and then a discrete circular act ive contour (DCA C) is created with this point as its centre. The DCA C is then moved under the influence of internal and external forces until it reaches equilibriu m, and the pupil is then localised.

Princi pal of Hough Transform
In an image, a curve "in any form" can be defined by a set of points. There is generally a set of parameters that lin ks these points by their spatial informat ion, or coordinate informat ion in the image space. So it means that the curve is parameterized and can be modeled by a mathematical equation that gives the relationship between the two sets (for examp le, the equation of a line, circle...).
Thus, the general principle of the Hough transform is a projection of the N-dimensional image space (denoted by I and defined by its variable i = 1: N) to a parameter space with a dimension M (denoted by H and defined by its

Hough Transform for Circles Detection
The Hough transform can be applied to detect the presence of a circu lar shape in a given image. It is used to detect any shape or to locate the iris in the face [10].
The characteristic equation of a circle of radius r and center (a, b) is given by:

-Case of known radius
If we know the radius of the circle to be detected in the image, the parameter to search is reduced to a pair (a, b) and the H space is 2 dimensional.
We consider a circle of radius R and center ) , (

Iris Detection System
Before the Hough transform is applied to the image, there was an edge detection technique used for finding the edges in the input image. First, we convert the image into the gray scale. Then extract the essential informat ion of contour present in the image. For this, we choose the 'prewitt filter' to extract the contour image. After the circles are detected and drawn on the original image then, the pattern of the iris is extracted and stored. A simp le overview o f the corresponding steps is shown in figure 5.
The next step consists to apply our method required the following steps: After creating an accu mulator h with the same dimension of the image, we extract the contour of image with the Prewitt filter. Then a model of the circle that satisfies the equation: , where r is the radius, is created.
The second step consists of taking each circle with a radius Ri, we do a scan of image on the contour and placing the circle on each non-zero point of this picture (contour), and increment each position of points (xi, yi) of the accumulator by one for each intersection of all point with any point of contour.
In the final step, we locate the position Xi and Yi of N ma ximu m points of accumulator; N represents the number of radius to search.
We can summarize this work as follows: -Read RGB Image: Converting the RGB image into grayscale level.
-Ext ract the contour by the Prewitt filter (b inary image).
-Introduce the variat ion range of the iris radius (in pixe ls) -Creation of models and centralize of circles.
-Search and locate the position of the maximu ms in accumulator.
-Ext ract the positions X0i, Y0i for each radius ri.
-Display the image and the circles found satisfying The research of parameters that define the circles has been limited with centers ) , ( 0 0 y x and radius r. To get a good results, we give each radius corresponds to an interval of iris rays. Therefore, the result will be more circles where their intersection with contour corresponds to set of points. The intersection of several circles with a single point of contour represents a point the accumulator. For the position of the circle to look for, we will seek the maximu m of the accumulator. We note that the accumulator (h) p resents two maximu ms indicate the most intersection points of circles in with contour. Their contact centers indicate irises centers.
The maximu ms resulting fro m the accumu lator is a matrix of size (1x2xN) for both variables X 0 and Y 0 . Where, N is the number of radius to research.
We can explain this principle as described in figure 6; the example shows that the Hough transform applied on the left eye image demonstrates the intersection of seven circles corresponding to the solution (radius) of accumu lator.

Simulation Results
We tested our algorith m on the "Caltech database" available on the Web [9], with 396 indiv iduals with a number of 24 frames per individual for d ifferent poses. The images are: 24 bit -RGB, 576 x 768 p ixels, file format : jpg. The proposed algorithm is implemented in MATLAB7.0; on Intel processor with 712M B RAM 2 GHz.

Results of Iris Detecti on
The experimental results have shown that the proposed algorith m gives better results. The algorith m accurately extracted irises of 379 images out of 396 images giving a success rate of 95 %. Fig 7 represents the better results of iris detection. In our experiments, the range of radius variation is fro m 6 to 11 pixels. Th is interval depends of a lot of parameters like: size of images, age…etc. Using the Hough transform for circles, we find peaks in accumulator; we find also spatially separated circles. We save the coordinates of integer points close to a circle of radius R in an accumulator mat rix. The plot of accumu lator in 3D demonstrates the iris position in the initial image (see Fig 8).  Table 1 shows the coordinates of the two circles found in image. The algorith m demonstrates also results of false detection as mentioned in Fig 9.

Effect of Noise on the Iris Detection
Our algorithm was tested on noisy images by adding Gaussian noise with zero mean (m = 0) and variance σ .
The density of probability is expressed by the equation: After adding noise to images, we obtained the following results: Our experiments demonstrate bad detection results for a threshold grater than 0.1.
Our algorithm was also tested on a part of the face image like eyes and other shapes. For example, the eye region can be extracted using a manual detection. The Hough transform permits us to detect correctly the iris for the most number of images ( fig 11).

Application Of Iris Detecti on in Different Col or Space
√ YCbCr Color Space: The YCbCr co lor space was introduced in image coding for video. In the case of color images, it allo ws to compensate the errors in transmission of information. Fro m the original image, we make a transformation fro m RGB to YCb Cr space by applying the following rules [ (9) After conversion of RGB color to YCb Cr colo r, we applied our algorith m on different images. We obtained the results listed below.

Figure 12. Examples of iris detection in YCbCr color
The results of YCb Cr co lor applicat ion gives 66.1% detection of the two irises, 29.5% detection of a single iris and 4.3% of undetected iris.
Bad results are obtained; this is due to the detection of circular objects on clothing or on the back plan situated behind the people. See below some examples presented bad detection.

√ YIQ Color Space
The YIQ colo r space was explicitly designed to support color television, wh ile allowing backwards compatib ility with black and wh ite TVs. It is still used today in non-HDTV color television broadcasting in the United States [17].
Conversion fro m RGBA to YIQA can be done using the color matrix [17]: . 0 (10) The application of YIQ Co lor Space gives 70.4% detection of the two irises, 24.3% detection of a single iris and 5.2% false detection (no iris detection).

Conclusions
We've presented in this article the circular hough transform for iris detection. Ou r method consists to search circles in contours image. The detection of contours plays a very important role in the detection of iris. The algorithm was applied to color image. The results depend on the influence of many parameters such as: The conditions for image capture are a very impo rtant factors for good or bad detection for examp le the lighting and the position of the human (position of the iris on face). We note that the position of the iris plays a very important role in the detection results. A recognition rate about 95 % was obtained. The hough transform achieves also good results in HSV and YCb Cr space. Bad results were obtained for noised images when the variance of Gaussian noise exceeds the value 0.1.
Our method can be tested in several applicat ions such as biometric systems, hu man mach ines interfaces, person identification, etc.