18-12-2012, 04:33 PM
Iris Biometrics for Embedded Systems
Iris Biometrics for Embedded Systems.pdf (Size: 1.13 MB / Downloads: 40)
Abstract
In many applications user authentication has to be
carried out by portable devices. Usually these devices are personal
tokens carried by users, which have many constraints regarding
their computational performance, occupied area, and power consumption.
These kinds of devices must deal with such constraints,
while also maintaining high performance rates in the authentication
process. This paper provides solutions to designing such personal
tokens where biometric authentication is required. In this
paper, iris biometrics have been chosen to be implemented due to
the low error rates and the robustness their algorithms provide.
Several design alternatives are presented, and their analyses are
reported.With these results, most of the needs required for the development
of an innovative identification product are covered. Results
indicate that the architectures proposed herein are faster (up
to 20 times), and are capable of obtaining error rates equivalent
to those based on computer solutions. Simultaneously, the security
and cost for large quantities are also improved.
INTRODUCTION
BIOMETRICS is the only method capable of recognizing
human beings using the real features of the user instead
of his or her knowledge (e.g., passwords) or belongings (e.g., a
magnetic stripe card) [1]. Among currently existing biometric
modalities, iris recognition is considered to be one of the most
secure and reliable technologies [2], [4], [6], [5]; however,
while matching algorithms in iris recognition are straightforward,
the signal processing prior to matching requires a
significant amount of processing power.
Biometric applications can be classified into two major
groups: identification and authentication. Identification is
performed when the user identity is not provided, wherein
the system must find the user from a database of biometric
data from all enrolled users. In contrast, authentication, is the
process of checking the identity of the user using provided
biometric data. Currently, both applications are ubiquitously
used; however, this paper will focus on authentication, as this
application is where personal tokens play an important role.
STATE OF THE ART IN IRIS BIOMETRICS
From a conceptual point of view, most iris recognition
systems have the same block diagram as any other biometric
modality (see Fig. 1). After capturing an image of the eye,
the iris is located and segmented to extract its features; these
features are then compared to a previously stored template [6].
This section describes each of these blocks in detail, providing
information on the approaches found in previous publications.
IMPLEMENTATION
Previous studies have shown the viability of creating
match-on-token solutions by including the comparison algorithm
within the token, providing an answer that deals with
the matching result [7]. In this paper, these studies have been
extended to analyze the viability of integrating the feature
extraction block within the personal token. With this solution,
simplification of the point of service terminal is achieved, and
security is improved.
The terminal, in the proposed architecture, should perform
the following tasks.
• Image Acquisition: The iris is captured with an infrared
camera, as previously mentioned. The cost and size of the
electronics and lens required for this task are not commercially
viable for insertion into the personal token.
• Image Segmentation: This preprocessing block is related
to the image acquisition. The non-detection of the iris or
the quality of the captured images are typical reasons for
rejection of the acquired image, thus, requiring a new capture
process. If this block were included in the token, many
images would have to be transferred from the terminal to
the token, increasing data communication and therefore the
verification time.