Anda di halaman 1dari 4

BIOMETRIC AUTHENTICATION USING HUMAN EAR AND IRIS

AbstractBiometric identification methods have proved to be very efficient, more natural and easy for users than traditional methods of human identification. Biometric authentication systems are essentially pattern recognition systems, the physiological characteristics being fingerprint, face, and hand geometry, DNA and iris recognition. The main aim of the project is to develop a biometric authentication system using the ear and also using eye (iris). Index TermsPattern recognition; biometric authentication; iris recognition, ear recognition.

records in less than a second. The iris image remains stable from the age of about 10 months up until death. II. RELATED WORK A. Ear Biometric Ear biometrics has received scant attention compared to the more popular techniques of automatic face, eye, or fingerprint recognition. However, ears have played a significant role in forensic science for many years, especially in the United States, where an ear classification system based on manual measurements was developed by Iannarelli, and has been in use for more than 40 years [17].Rutty et al. have considered how Iannarelli's manual techniques might be automated [24] and a European initiative has looked at the value of ear prints in forensics [12].Hurley et al. used force field feature extraction [14, 15, 16] to map the ear to an energy field which highlights potential wells and potential channels as features. Abdel-Mottaleb et al. [1] used the force field transform to obtain a smooth surface representation for the ear and then applied different surface curvature extractors to gather the features. Akkermans et al [2] developed an ear biometric system based on the acoustic properties of the ear. They measure the acoustic transfer function of the ear by projecting a sound wave at the ear and observing the change in the reflected signal. Scandia Corp. patented a similar technique [20].An approach of extracting features from the ear image using Haar wavelet decomposition technique has been adopted by Computer Science department of IIT, Kanpur. Haar wavelet decomposition is applied on ear images and the extracted wavelet coefficients represent the pattern of the ear. Decision regarding identification depended on matching one test image with n trained images using Hamming distance algorithm. This study has for the first time incorporated soft ear biometrics information to improve upon the identification performance. B. Eye Biometric Eric Sung, Xilin Chen, Jie Zhu and Jie Yang, December 2002, proposed a modified Kolmogora, complexity measure based on maximum Shannon entropy of wavelet packet reconstruction to quantify the iris information. Real time eyecomer tracking, iris segmentation and feature extraction algorithms are implemented. Video images of the iris are captured by an ordinary camera with a zoom lens. Jiali Cui, Yunhong Wang, JunZhou Huang, Tieniu Tan and Zhenan Sun have proposed [8] the iris recognition algorithm based on PCA (Principal Component Analysis) is first introduced and then, iris image synthesis method is presented. The synthesis method first constructs coarse iris images with the given coefficients. Then, synthesized iris images are enhanced using

I. INTRODUCTION Biometrics is the science of identifying or verifying the identity of a person based on physiological or behavioral characteristics. Physiological biometrics use algorithms and other methods to define identity in terms of data gathered from direct measurement of the human body. Finger print and finger scan, hand geometry, palm prints, Iris and retina scanning and facial geometry are all examples of physiological biometrics. Behavioral biometrics is however defined by analyzing a specific action of a person. Examples of these include voice identification, signature dynamics, keystroke dynamics and motion recognition. In proposing the ear as the basis for a new class of biometrics, there is the need to show that it is viable (i.e., Universal, unique, Permanent, Collectable). In the same way that no one can prove that fingerprints are unique, there is no absolute way to show that each human has a unique pair of ears. It is obvious that the structure of the ear does not change radically overtime. Since every individual has ears, it is rational to conclude that the ear is universal. The ear is also collectable using various means. Unlike the face, the ear is a relatively stable structure that does not change much with the age and facial expressions. The shape does not change due to emotion as the face does, and the ear is relatively constant over most of a persons life. The human iris is so unique that no two irises are alike, even among identical twins, in the entire human population. Recently, human iris biometric based identification has attracted the attention of research and development community. Iris recognition has many advantages over the other forms of biometric identification. Iris recognition is the most accurate form of identification known to man. It is also capable of making a match from a database of over 1 million

super resolution. Through controlling the coefficients, they create many iris images with specified classes. Extensive experiments show that the synthesized iris images have satisfactory cluster and the synthesized iris databases can be very large. III. METHODOLOGY A. Ear biometric Histogram equalization is a technique used for adjusting image intensities to enhance contrast.

Gray Image

Dilated Image
Gray Image
Hist Equalised

800 700

1200

1000

600 500 400 300


400 800

600

200 100 0 0 50 100 150 200 250


200

0 0 50 100 150 200 250

Histogram of the image

Equalized histogram

The dilation process is performed by laying the structuring element B on the image A and sliding it across the image in a manner similar to convolution (will be presented in a next laboratory). The difference is in the operation performed. It is best described in a sequence of steps: 1. If the origin of the structuring element coincides with a 'white' pixel in the image, there is no change; move to the next pixel. 2. If the origin of the structuring element coincides with a 'black' in the image, make black all pixels from the image covered by the structuring element. Notation:

Gabor filters are able to provide optimum conjoint representation of a signal in space and spatial frequency. A Gabor filter is constructed by modulating a sine/cosine wave with a Gaussian. This is able to provide the optimum conjoint localization in both space and frequency, since a sine wave is perfectly localized in frequency, but not localized in space. Modulation of the sine with a Gaussian provides localization in space, though with loss of localization in frequency. Decomposition of a signal is accomplished using a quadrature pair of Gabor filters, with a real part specified by a cosine modulated by a Gaussian, and an imaginary part specified by a sine modulated by a Gaussian. The real and imaginary filters are also known as the even symmetric and odd symmetric components respectively. The center frequency of the filter is specified by the frequency of the sine/cosine wave, and the bandwidth of the filter is specified by the width of the Gaussian.
Gray Image

A B

Gabour Result

constants of the Gaussian envelope along 'x and ' y axes respectively. Further details of Gabor filters may be found in [10][12]. The frequency parameter f is often chosen to be of power 2. In our experiments, the central frequencies used are 2, 4, 8, 16, and 32 cycles/degree. For each central frequency f, filtering is performed at 0 , 45 ,90= and 135 . So, there are a total of 20 Gabor filters with different frequencies and directions. Each sub image is respectively filtered by these Gabor filters. This leads to a total of 160 (20 for each sub image) output images from which the iris features are extracted. The choices of the parameters of Gabor filters are discussed in [14].
GABOR FEATURES

Template generation: After obtaining the gabor result, a template is generated using specific equations. This template will be the final feature added in the database.

Ear Template

Template generation: After obtaining the gabor result, a template is generated using specific equations. This template will be the final feature added in the database. B. Eye biometric The iris is the area of the eye where the pigmented or colored circle, usually brown or blue, rings the dark pupil of the eye. Iris Recognition systems can be explained as follows: I. Acquisition. II. Iris Preprocessing. An iris recognition system uses a video camera to capture the sample while the software compares the resulting data against stored templates. In recent years, Gabor filter based methods have been widely used in computer vision, especially for texture analysis. Gabor elementary functions are Gaussians modulated by sinusoidal functions. It is shown that the functional form of Gabor filters conforms closely to the receptive profiles of simple cortical cells, and Gabor filtering is an effective scheme for image representation.

Iris Template

Template fusion: The ear template and iris template are combined to form a single template.

IV. CONCLUSIONS This project was aimed at developing a biometric authentication system based on human ear and eye images. An invariant geometrical method was used in order to extract features needed for classification. After the feature extraction, authentication is performed based on simple comparison between a new input image and an already existing one.

Where f is the frequency of the sinusoidal plane wave along the direction from the x-axis, ' x and ' y are the space

For easy images from the database, error-free recognition was obtained. When all the external conditions such as lighting are effectively controlled and remain constant, the system produces a perfect performance with accurate results all the time. In spite of the excellent results produced when all the conditions remain constant, the system does not produce accurate results when the conditions are varied. For example, when there are illumination variations, the features extracted from the different raw data taken tend to be different and hence do no produce an accurate match even though the all belong to the same person. When the conditions vary, the percentage matches reduce thus leading to some false rejections. These problems will serve as a basis for future work that will be carried out. In order to achieve satisfactory results complex images and images taken under varying conditions, the contour detection algorithm has to be improved so that long, straight line-contours of glasses and artificial contours of earrings and hair are eliminated before applying feature extraction algorithm.

V. REFERENCES 1.M. Abdel-Mottaleb, J. Zhou, Human Ear Recognition from Face Profile Images, ICB 2006, pp. 786 - 792. 2.H. M. Akkermans, T. A. M. Kevenaar, D. W. E. Schobben, Acoustic Ear Recognition for Person Identification, Fourth IEEE Workshop on Automatic Identification Advanced Technologies (AutoID'05) pp. 219-223 3.Banafshe Arbab-Zavar, Mark S. Nixon, and David J. Hurley, On Model-Based Analysis of Ear Biometrics 4.M. Burge, W. Burger, Ear biometrics in: Jain, Bolle and Pankanti (Eds.), Biometrics: Personal Identification in Networked Society, Kluwer Academic, Dordrecht, 1998, pp. 273-286. 5.Burge, M., and Burger, W., Ear biometrics in computer vision, Proc. ICPR 2000, 822-826, 2002 6.A. Bertillon, La photographie judiciaire, avec un appendice sur la classification et l'identication anthropometriques, Gauthier-Villars, Paris, 1890. 7.K. Chang, K.W. Bowyer, S. Sarkar, B. Victor, Comparison and combination of ear and face images in appearance-based biometrics, IEEE Trans. PAMI, 2003, vol. 25, no. 9, pp. 11601165. 8.H. Chen, B. Bhanu, R. Wang, Performance evaluation and prediction for 3D ear recognition, Proc. International

Conference on Audio and Video based Biometric Person Authentication, NY, 2005. 9.H. Chen, B. Bhanu, Contour matching for 3-D ear recognition, Proc. IEEE Workshop on Applications of Computer Vision, Colorado, 2005. 10.H. Chen, B. Bhanu, Human ear recognition in 3-D, Proc. Workshop on Multimodal User Authentication, Santa Barbara, CA, 2003, pp. 91-98. 11. M. Choras, Ear Biometrics Based on Geometrical Feature Extraction, Electronic Letters on Computer Vision and Image Analysis (Journal ELCVIA), 2005, vol. 5, no. 3, pp. 84-95. 12.L. Meijermana, S. Shollb, F. De Contic, M. Giaconc,C. van der Lugtd, A. Drusinic, P. Vanezis, G. Maata, Exploratory study on classification and individualisation of earprints, Forensic Science International 140 (2004) 91-99 13. D. Hurley, J.,Arbab-Zavar, B. and Nixon, M. S. (2007) THE EAR AS A BIOMETRIC. In EUSIPCO 2007 , 2007 14. Hurley, D. J., Nixon, M. S. and Carter, J. N. Force Field Energy Functionals for Image Feature Extraction. Proc. 10th British Machine Vision Conference, 1999, 604-613 15. D. J. Hurley, Force Field Feature Extraction for Ear Biometrics. PhD Thesis 2001, Electronics and Computer Science, University of Southampton. 16. D. J. Hurley, M. S. Nixon, J. N. Carter, Force field feature extraction for ear biometrics, Computer Vision and Image Understanding, 2005, vol. 98, pp. 491-512. 17.A. Iannarelli, Ear Identification, Paramount Publishing Company, Freemont, California, 1989 18.K. Iwano, T. Hirose, E. Kamibayashi, S. Furui, AudioVisual Person Authentication Using Speech and Ear Images, Proc. of Workshop on Multimodal User Authentication, 2003, pp.85-90. 19.Erno Jeges, MODEL-BASED HUMAN EAR IDENTIFICATION 20.Hanna-Kaisa Lammi, EAR BIOMETRICS 21.Jiali Cui, Yunhong Wang, JunZhou Huang, Tieniu Tan and Zhenan Sun, An Iris Image Synthesis Method Based on PCA and Superresolution, 17th International Conference on Pattern Recognition (ICPR04), 2326 August 2004, Cambridge, UK, Volume 4, pp. 471474.

Anda mungkin juga menyukai