Feature extraction for different distances of visible reflection iris using multiscale sparse representation of local Radon transform
Anis Farihin Mat Raffei, Hishammuddin Asmuni, Rohayanti Hassan, Razib M. Othman
a Laboratory of Biometrics and Digital Forensics
b Laboratory of Biodiversity and Bioinformatics
c Laboratory of Computational Intelligence and Biotechnology, Faculty of Computer Science and Information Systems, Universiti Teknologi Malaysia (UTM), Skudai, 81310 Johor, Malaysia
Iris recognition is a promising method by which to accurately identify a person. During the iris recognition stage, the features of the iris are extracted, including the unique, individual texture of the iris. The ability to extract the texture of the iris in non-cooperative environments from eye images captured at different distances, containing reflections, and under visible wavelength illumination will lead to increased iris recognition performance. A method that combined multiscale sparse representation of local Radon transform was proposed to down sample a normalized iris into different lengths of scales and different orientations of angles to form an iris feature vector. This research was tested using 1000 eye images from the UBIRIS.v2 database. The results showed that the proposed method performed better than existing methods when dealing with iris images captured at different distances.
The authors highly appreciate the contribution of University of Beira Interior for providing the UBIRIS.v2 database and of Masek for providing the codes. This research has been funded by GATES Scholars Foundation (GSF) of GATES BIOTECH Solution Sdn. Bhd. company (grant no. LTRGSF/SU/2011-04) and MyMaster Scholarship of Ministry of Higher Education Malaysia.
Local radon transform; Iris recognition; Feature extraction; Non-cooperative environment; Visible iris.
An improved multiscale retinex algorithm for motion-blurred iris images to minimize the intra-individual variations
D’yia Sarah Md Shukri, Hishammuddin Asmuni, Rohayanti Hassan, Razib M. Othman
Laboratory of Biometrics and Digital Forensics, Faculty of Computer Science and Information Systems, Universiti Teknologi Malaysia, 81310 Skudai, Johor, Malaysia
Motion-blurred iris image is caused by less user cooperation, poor quality cameras and environmental conditions when capturing image, thus contributing to a variety of iris patterns, which are due to the shadows and noises occurring in the image. The biggest challenge dealing with motion-blurred iris image is to analyze the exact pattern of the iris image. The combination of homomorphic filtering and multiscale retinex algorithms can cope with the illumination changes and shadow removal in order to produce enhanced iris pattern. Homomorphic filtering is applied to remove shadows on motion-blurred image. The processed image that is free of shadows is then applied with multiscale retinex algorithm to improve the contrast of the image. The enhanced iris pattern that is free of shadows is then evaluated using intensity histogram to validate the proposed method. The accuracy of the proposed method is 99.2% with minimum false rejection and false acceptance rate.
Thanks to my supervisor and co-supervisors for various helpful discussions during this research. This research supported by GATES BIOTECH Solution Sdn. Bhd under the scheme of GATES Scholars Foundation (GSF), reference no: LTR/GSF/SU/2011-03.
Homomorphic filtering; Motion-blurred iris; Multiscale retinex