Printer Friendly

Iris recognition with phase--only correlation.


Biometrics is a popular security criterion to restrict access to some systems and preserve their security. A part of biometrics is human eye iris recognition or matching. From the several methods developed in the past years, the phase-only correlation (POC) (Chien, 2004; Ito et al., 2004; Ito et al., 2005; Miyazawa et al., 2005) is important because its sub-pixel image translation capability. The past experiments developed a modified POC by rectangular band filtering the cross-spectrum of the POC function (BPOC) (Ito et al., 2004; Ito et al., 2005) in order to improve the genuine-impostor rejection.

This paper presents a theoretical introduction and some experiments for evaluating recognition performances of the proposed method and the dedicated ones.


2.1 Phase only cross-correlation

The recognition process is used for object registration which means that one object is "compared" with several objects. Comparison criteria concludes if the compared objects are or not similar with other objects. The comparison process basically works with two objects. In our case the comparison method is the phase-only correlation while the objects are the human eye irises.

In a single cross-correlation process the two objects are denoted as reference and non-reference. That means that from the cross-correlation process we obtain the information if the reference is similar or not with the non-reference object. The cross-correlation considers two (NxM) images, ref(x, y) as reference image and nref (x, y) as non-reference image. The 2D discrete Fourier transforms of these images, are denoted as Ref(u,v) and NRef(u,v),

The phase-only cross-spectrum (Ito et al., 2005; Ito et al., 2004; Miyazawa et al., 2005; Miyazawa et al., ICB 2006) is defined by


where [[phi].sub.rn](u,v) is the phase difference between the reference and the non-reference 2D discrete Fourier transforms. Thus, if ref(x,y) = nref(x,y) then [DELTA][[phi].sub.rn] (u,v) = 0, the phase-only cross-correlation is given by


This means that if the two images are identical then the POC gives a highly sharp peak so the matching accuracy is higher than in the classical method.

2.2 Band limited and elliptic band limited phase-only cross- correlation

The cross-correlation process on a database is basically characterized by the cross-correlation peak intensity (CPI).

Phase-only correlation is a very precise matching method and effective for the verification process. This is done by "fine comparing" of the high frequencies in the Fourier transforms of the irises.

When one has to register a new iris then the correlation process must match it with some deformed representations of it gathered in a class. The deformations alter exactly the high frequencies of the Fourier transform. The intra-class correlation can have a lower CPI value than the inter-class correlation CPI value. This means that the involved matching process fails.

Iris database registration matching process has to correlate only the low frequencies that are common to all irises from the same class. This is the reason why the band limited phase only correlation (BPOC) (Ito et al., 2005; Ito et al., 2004; Miyazawa et al., 2005; Miyazawa et al., ICB 2006) was introduced. This correlation uses a 2D band filter on the phase-only cross- correlation spectrum. The band filter is defined with two sub- unitary valued coefficients: over the rows direction, cL and over the columns direction cC .

In this paper the author proposes an elliptic band phase- only correlation, (EPOC). In this method, there is used an elliptic band filter with the same cL and cC parameters instead of a rectangle band filter with cL and cC parameters. The reason of this choice is that the power spectrum of the irises usually presents the highest density of the information in a centered elliptic form. As mentioned before, this centered ellipse contains that kind of spatial frequencies that can accommodate the database iris registration.


In this paper, an iris database was used which was captured with a CCD camera in 320 x 240 pixels image size (Portions of the research in this paper use the CASIA-IrisVl collected by the Chinese Academy of Sciences' Institute of Automation (CASIA))(figure 1a).

The database contains iris classes with 3 scanned irises for each of the 12 persons. The iris index denotes "ppp_e_s.bmp", as ppp is the person number, e is the eye number (1 for left, 2 for right) and s is the number of the iris scan.

Before the iris recognition process is important to localize and to clip only the clear part of the iris (without noise as eyelashes, reflections, eyelids, pupils) (figure 1b).



For a better pattern recognition performance it was done a polar transformation of the localized and clipped iris image (figure 1c). These kinds of images were used in the phase-only recognition processes. The experimental results from the BPOC and EPOC are presented in figure 2 a, b and figure 3 a, b. The band limited BPOC and EPOC parameters were selected with the values: cL = 0.35 and cC = 0.80.

We presented the Genuine Acceptance Rate, GAR, and the False Acceptance Rate, FAR dependences. It can be denoted from these diagrams that the EPOC performances in iris recognition has the best performances than the POC and BPOC methods. The reason is that the GAR increases faster with far for the EPOC than the BPOC and the POC correlation methods. The same thing can be denoted from figure 3a where was presented the GAR values when FAR = 0.020 .

Equal error rate ( EER ) is an important quantitative pattern recognition coefficient that is calculated from the FAR-FRR diagram over a certain CPI threshold domain. Thus EER is threshold independent and it gives accurate comparison between the pattern recognition methods over the same database. The lower the EER value is, the better the performance in pattern recognition, is.

Thus the POC has the lower EER value, and then comes the EPOC with a greater eer value and BPOC with the highest EER value. This means that from the EER point of view the POC method has the best pattern recognition performances, then comes the EPOC and the last is BPOC.



In this paper, there are presented three phase-only correlation methods: POC, the rectangle band limited, BPOC, and the proposed elliptic band limited, EPOC. These matching methods are very efficient for iris recognition (database experiment). The results in figures 2 and 3 emphasize that elliptic band limited phase-only correlation, EPOC, has overall better performances--higher GAR values and intermediate EER value--than the POC and the rectangle band limited phase-only correlation, BPOC. Thus, for human eye iris database registration, the EPOC method is more efficient than the POC and BPOC method.

Our future research will develop a more robust EPOC method to geometrical deformations of the irises that can involve a normalized iris with Log-Polar transform. Another future plan is to work with much larger iris database to ensure statistical significance so as to be able to use it in biometrics technology.


Chien, L. H. & Aoki T.(2004). Robust motion estimation for video sequences based on phase-only correlation, Proceedings of the 6th IASTED SIP 2004, Hamza M.H. (Ed), pp. 441-446, ISBN 0-88986-434-9, Honolulu, USA, Aug. 2004, ACTA Press, Canada

Ito, K.; Nakajima H.; Kobayashi K. & Aoki T., Higuchi T. (2004). A fingerprint matching algorithm using phase-only correlation, IEICE Transactions. Fundamentals, E87-A, No. 3, March 2004, pp. 682-691, ISSN 1745-1337

Ito K.; Morita A.; Aoki T.; Higuchi T.; Nakajima H. & Kobayashi K. (2005). A fingerprint recognition algorithm using phase-based image matching for low-quality fingerprints, Proceedings of IEEE Int. Conf. on Image Processing, pp. II-33-II-36, ISBN: 0-7803-9134-9, September 2005, Genova, Italy, IEEE, NJ USA

Miyazawa K.; Ito K.; Aoki T.; K. Kobayashi & Nakajima H. (2005). An efficient iris recognition algorithm using phase-based image matching, Proceedings of IEEE Int. Conf. on Image Processing, pp. II-49-II-52, ISBN: 0- 7803-9134-9, September 2005, Genova, Italy, IEEE, NJ USA

Miyazawa K.; Ito K.; Aoki T.; K. Kobayashi & Nakajima H.a (ICB 2006). A phase-based iris recognition algorithm, In: Lecture Notes in Computer Science 3832, D. Zhang and A.K. Jain (Ed.), ISBN 3-540-3111-4, pp. 356-365, Springer-Verlag Berlin Heidelberg Germany
COPYRIGHT 2009 DAAAM International Vienna
No portion of this article can be reproduced without the express written permission from the copyright holder.
Copyright 2009 Gale, Cengage Learning. All rights reserved.

Article Details
Printer friendly Cite/link Email Feedback
Author:Teusdea, Alin Cristian; Gabor, Gianina
Publication:Annals of DAAAM & Proceedings
Article Type:Report
Geographic Code:4EUAU
Date:Jan 1, 2009
Previous Article:Synthesis of the adaptive control system with tuning of the input signal parameters.
Next Article:Developing a brain-computer-based human-robot interaction for industrial environments.

Terms of use | Copyright © 2018 Farlex, Inc. | Feedback | For webmasters