Real-time iris segmentation and its implementation on FPGA
- PDF / 1,836,374 Bytes
- 14 Pages / 595.276 x 790.866 pts Page_size
- 75 Downloads / 232 Views
ORIGINAL RESEARCH PAPER
Real‑time iris segmentation and its implementation on FPGA Tariq M. Khan1 · Donald G. Bailey2 · Mohammad A. U. Khan3 · Yinan Kong4 Received: 12 April 2018 / Accepted: 19 February 2019 © Springer-Verlag GmbH Germany, part of Springer Nature 2019
Abstract This paper presents a real-time iris segmentation technique that is well suited to a fast implementation on an FPGA. One major hurdle associated with iris segmentation techniques is the use of iterative processes that lead to expensive hardware implementations. To circumvent this, the proposed algorithm uses the sign image obtained from subtracting the background, along with morphological operators to localise the pupil. The outer boundary is located by first normalising a selected image region that contains the iris, and then using a first-order gradient operator. The proposed non-iterative algorithm is implemented on an FPGA. Four near infrared (NIR) iris public databases, namely: CASIA-IrisV3-Lamp, MMU v1.0, ND-IRIS-0405 and NIST ICE 2005, are used to test the proposed algorithm. The proposed method for iris segmentation and normalization gives much better accuracy than the existing state-of-the-art methods implemented on hardware. The proposed realisation requires about 45% fewer logic registers and 52% fewer logic elements than the existing state-of-the-art implementations. Keywords Pupil segmentation · Pupil localization · Region properties
1 Introduction Biometrics is a developing technology that provides a higher level of security, convenience and efficiency than traditional password methods for user authentication. The primary advantage of biometric-based authentication is that it cannot be forgotten, stolen or misplaced. Humans have many biometric features such as face conformation, hand geometry, fingerprint, voice, and iris. Iris recognition is accurate and reliable due to its high degree of uniqueness and randomness, even between identical twins and remains constantly stable throughout an adult’s life [1, 2]. It is observed that iris patterns have a high dimensionality that makes the recognition decision very reliable [1]. * Tariq M. Khan [email protected] 1
Department of Electrical and Computer Engineering, COMSATS University Islamabad, Islamabad, Pakistan
2
School of Engineering and Advanced Technology, Massey University, Palmerston North, New Zealand
3
Biometric and Sensor Lab, Effat University, Jeddah, Saudi Arabia
4
School of Engineering, Macquarie University, Sydney, Australia
In general, an iris recognition system acquires iris images either in the visible wavelength range (VW) (400–700 nm) or in the near infrared range (NIR) (700–900 nm) of the electromagnetic spectrum. NIR images are obtained where subjects are asked to stop and then stare into the acquisition system at close range, whereas for VW, subjects are even allowed to walk slowly. This affects the quality of images acquired. In NIR images, the pupil region is usually quite prominent and is easy to extract even without extracting the iris bo
Data Loading...
