19-06-2012, 02:28 PM
A Novel Finger Vein Pattern Extraction Method Using Oriented Filtering Technology
[attachment=24803]
Abstract
To extract finger vein features effectively and
efficiently, a novel algorithm based on oriented filter for finger
vein extraction is proposed. The proposed algorithm calculates a
direction map and uses a group of designed oriented filters to
facilitate the extraction of the characteristic vein pattern from
the enhanced finger vein image. Experimental results show that
this new algorithm not only extracts smooth and continuous vein
features, but also effective in removing noise from low-quality
images.
Index Terms - finger vein extraction. directional image.
oriented filter.
I. INTRODUCTION
Smart recognition of human identity for security and
control is a global issue of concern in our world today. The
losses due to identity fraud can be substantial in terms of
money and confidentiality. Hence there are quite a number of
Automatic Authentication Systems used in applications such
as access control systems, criminal identification, autonomous
vending and automated banking among others. Among the
many authentication systems that have been proposed and
implemented, biometrics is emerging as the most foolproof
method of automated personal identification. Fingerprints
have been the most widely used and trusted biometrics. The
reasons being: the ease of acquiring fingerprints, the
availability of inexpensive fingerprint sensors and a long
history of its use. However, limitations like the deterioration
of the epidermis of the fingers, finger surface particles etc
result in inaccuracies that call for more accurate and robust
methods of authentication. Vein recognition technology offers
a promising solution to these challenges due the following
characteristics. (1) Its universality and uniqueness. Just as
individuals have unique fingerprints, so also they do have
unique finger vein images. The vein images of most people
remain unchanged despite ageing. (2) Hand and finger vein
detection methods do not have any known negative effects on
body health. (3) The condition of the epidermis has no effect
on the result of vein detection. (4) Vein features are difficult to
be forged and changed by surgery [1]. These desirable
properties make vein recognition a highly reliable
authentication method. Its recognition performance to a large
extent is closely related to the quality of vein object extraction.
The purpose of vein object extraction is to obtain vein ridge
from the background. The extraction has a direct impact on
feature extraction and feature matching [2]. Therefore vein
object extraction significantly affects the effectiveness of the
entire system.
Traditional vein extraction technology can be broadly
divided into three categories namely: segmentation techniques
based on region information, segmentation techniques based
on edge information, segmentation technology based on
particular theories and tools. Application of the traditional
single-threshold segmentation methods such as fixed
threshold, total mean, total Otsu etc, have a common
limitation such as difficulty in obtaining the desired accurate
segmentation results. However, using multi-threshold methods
like local mean and local Otsu, improve the results but these
still have problems like noise and the over-segmentation effect
[3],[4],[5],[6],[7],[8].
Reference [9] proposed an oriented filter method to
enhance fingerprint image. The method is according to the
ridge and valley feature of fingerprint image to eliminate noise
and enhance ridge line. Ref. [10] used the directionality
feature of fingerprint to present a fingerprint image
enhancement method based on orientation field. These two
methods take the directionality characteristic of the fingerprint
into account, so they can enhance and de-noise fingerprint
image effectively. Finger vein pattern also has textural and
directionality features, with directionality being consistent
within the local area. Inspired by methods in [9]and[10], we
proposed a finger vein pattern extraction method using
oriented filtering technology from the directionality feature of
veins. The proposed algorithm generates a directional image
of the finger vein image and a group of oriented filters, and
then extracts vein object from the enhanced oriented filter
image. Experimental results indicate that our method is a
better enhancement over the traditional NiBlack method [11],
[12], [13], and has good segmentation results even with lowquality
images. We present the procedures used in this method
in the following section.