23-08-2012, 12:50 PM
Iris Recognition Using Modified Hierarchical Phase-Based Matching (HPM) Technique
1Iris Recognition.pdf (Size: 457.55 KB / Downloads: 62)
Abstract
This paper explores an efficient algorithm for iris recognition
based on Hierarchical Phase-Based Image Matching (HPM)
technique. One of the difficult problems in feature-based iris
recognition is that the matching performance is significantly
influenced by many parameters in feature extraction process,
which may vary depending on environmental factors of image
acquisition. The proposed system is designed for applications
where the training database contains an iris for each individual.
The final decision is made by HPM at “matching score level
architecture” in which feature vectors are created independently
for query images and are then compared to the enrollment
templates which are stored during database preparation for each
biometric trait. Based on the proximity of feature vector and
template, each subsystem computes its own matching score.
These individual scores are finally combined into a total score,
which is passed to the decision module. In this proposed
technique, the use of phase components in 2D (two dimensional)
discrete Fourier transforms of iris images makes possible to
achieve highly robust iris recognition in a unified fashion with a
simple matching algorithm. The technique has been successfully
applied and also clearly demonstrates an efficient matching
performance of the proposed algorithm.
Introduction
Overview of the work
A major approach for IRIS recognition today is
to generate feature vectors corresponding to individual
iris images and to perform iris matching based on
different metrics. One of the difficult problems in feature
based iris recognition s that the matching performance is
significantly influenced by many parameters in feature
extraction process, which may vary depending on
environmental factors of image acquisition. This paper
presents an efficient algorithm for iris recognition using
hierarchical phased-based matching (HPM). It eliminates
steps like normalization and eyelid masking and also
improves the speed of matching by hierarchical based
matching method.
Existing work
The aim of biometrics is to identify individuals
using physiological or behavioral characteristics such as
fingerprints, face, iris, retina, and palm prints. Among
many biometric techniques, iris recognition is one of the
most promising approaches due to its high reliability for
personal identification [1]. The biometric person
authentication technique based on the pattern of the
human iris is well suited to be applied to any access
control system requiring a high level of security.
Compared to fingerprint, iris is protected from the
external environment behind the cornea and the eyelid.
No subject to deleterious effects of aging, the small-scale
radial features of the iris remain stable and fixed from
about one year of age throughout life. For Iris recognition,
R.Wildes solution includes (i) a Hough transform for iris
localization, (ii) Laplacian pyramid (multi-scale
decomposition) to represent distinctive spatial
characteristics of the human iris, and (iii) modified
normalized correlation for matching process [2]. In
matching two irises, Daugman’s approach involves
computation of the normalized Hamming distance
between iris codes, whereas Wildes applies a Laplacian of
Gaussian filter at multiple scales to produce a template
and computes the normalized correlation as a similarity
measure [3]. J.Daugman’s and R.Sanchez-Reillo’s
systems are implemented exploiting (i) integrodifferential
operators to detect iris inner and outer
boundaries, (ii) Gabor filters to extract unique binary
vectors constituting iriscodeTM, and (iii) a statistical
matcher (logical exclusive OR operator) that analyses
basically the average Hamming distance between two
codes (bit to bit test agreement). Because of unified
reference database of iris images does not exist, a classic
performance comparison of the described systems is not
trivial.
Experimental Results
We tested our project on the database contains 105
gray scale eye images (256 x 128) with 15 unique eyes
and 7 different images of each unique eye. The algorithm
is implemented in MATLAB 7. We have implemented the
proposed hierarchical matching algorithm. The results are
tested on the Iris image database. Pertaining to the general
approach discussed in the previous sections,
corresponding to original image, circular edge detection
& pupil center localization, Upper and lower eyelid
masking, iris encoding and matching score are shown in
the following Fig. 5(a),5(b) respectively.
Conclusion
This paper presented a novel approach for the
efficient iris recognition using Hierarchical Phase-Based
Matching (HPM) algorithm. Thus the proposed approach
can give a highly accurate recognition. Meanwhile, using
this proposed method the computational time of phase
component has been reduced. The use of phase
component in 2D Discrete Fourier Transform of iris
images makes possible to achieve highly robust iris
recognition in a unified fashion with this proposed
matching algorithm.