Hough Transform and Active Contour for Enhanced Iris Segmentation
Iris segmentation is considered as the most difficult and fundamental step in an iris recognition system. While iris boundaries are largely approximated by two circles or ellipses, other methods define more accurately the iris resulting in better recognition results. In this paper we propose an iris segmentation method using Hough transform and active contour to detect a circular approximation of the outer iris boundary and to accurately segment the inner boundary in its real shape motivated by the fact that richer iris textures are closer to the pupil than to the sclera. Normalization, encoding and matching are implemented according to Daugmans method. The method, tested on CASIA-V3 iris images database is compared to Daugmans iris recognition system. Recognition performance is measured in terms of decidability, accuracy at the equal error rate and ROC curves. Improved recognition performance is obtained using our segmentation model proposing its use for better iris recognition system.
Keywords: Iris segmentation, Biometric, Hough transform, Active contour.
Download Full-Text
ABOUT THE AUTHORS
Alaa Hilal
Alaa Hilal received the BS degree in general physics in 2008 and the MS degree in medical imaging in 2010 both from the Lebanese University, Lebanon. He is currently working toward the PhD degree at the Lebanese University, Lebanon and the University of Technology of Troyes, France. He is actively involved in the development of robust iris recognition system. He has 3 publications in international conferences and journals. His current areas of interest include image processing, pattern recognition and biometrics.
Bassam Daya
Bassam Daya received the BE degree in electrical and computer engineering in 1992 from the Lebanese University, Lebanon, the MS degree in automatic control and applied computer in 1993 from the Ecole Centrale of Nantes, France and the PhD degree in automatic control and applied computer in 1996 from the University of Angers, France. He was an assisting professor from 1994 till 1998 in the University of Angers, France and worked as a research engineer from 1996 till 1998 in UNIVALOIRE Society, Angers, France. From 1998 till 2002 he was an assistant professor at the Lebanese University, IUT of Saida, Lebanon and after it an associated professor from 2002 till 2007 in the same university and he became since 2007 a full professor in the Lebanese university. He was awarded one of the top ten graduates of the 1991-1992 academic year presented by the cultural center Hariri in 1992 at the American University of Lebanon, Lebanon. He obtained the first prize in the annual competition LIRA of the Lebanese industrial research achievements of 2004 between all Lebanese universities on programming and telecommunications section. He obtained as well the third prize in the same section of the same competition LIRA for both years 2004 and 2005. He was the chief of many projects organized by CEDAR and Ministry of culture in Lebanon in 2006 and in 2009. He is the co-other of the best paper award on the 30th international conference on information systems, architecture and technology, Poland, 2009. He has more than 44 published papers. His current research interests are in neural network architecture for robotics systems, object detection and identification (face, vehicle, and elderly fall detection), iris recognition, learning Rules in the Purkinje cell system of the cerebellar cortex and its application to a bipedal robot.
Pierre Beauseroy
Pierre Beauseroy received his engineering degree in computer science and his master degree in complex system control from University of Technology of Compiegne in 1988. He received his PHD degree in complex system control from the same university in 1992. Since 1993 he is continuing his research at the University of Technology of Troyes. He is a full professor since 2010 and leads the system modeling and dependability team (LM2S) since 2011. His major research interests are pattern recognition and machine learning.
Alaa Hilal
Alaa Hilal received the BS degree in general physics in 2008 and the MS degree in medical imaging in 2010 both from the Lebanese University, Lebanon. He is currently working toward the PhD degree at the Lebanese University, Lebanon and the University of Technology of Troyes, France. He is actively involved in the development of robust iris recognition system. He has 3 publications in international conferences and journals. His current areas of interest include image processing, pattern recognition and biometrics.
Bassam Daya
Bassam Daya received the BE degree in electrical and computer engineering in 1992 from the Lebanese University, Lebanon, the MS degree in automatic control and applied computer in 1993 from the Ecole Centrale of Nantes, France and the PhD degree in automatic control and applied computer in 1996 from the University of Angers, France. He was an assisting professor from 1994 till 1998 in the University of Angers, France and worked as a research engineer from 1996 till 1998 in UNIVALOIRE Society, Angers, France. From 1998 till 2002 he was an assistant professor at the Lebanese University, IUT of Saida, Lebanon and after it an associated professor from 2002 till 2007 in the same university and he became since 2007 a full professor in the Lebanese university. He was awarded one of the top ten graduates of the 1991-1992 academic year presented by the cultural center Hariri in 1992 at the American University of Lebanon, Lebanon. He obtained the first prize in the annual competition LIRA of the Lebanese industrial research achievements of 2004 between all Lebanese universities on programming and telecommunications section. He obtained as well the third prize in the same section of the same competition LIRA for both years 2004 and 2005. He was the chief of many projects organized by CEDAR and Ministry of culture in Lebanon in 2006 and in 2009. He is the co-other of the best paper award on the 30th international conference on information systems, architecture and technology, Poland, 2009. He has more than 44 published papers. His current research interests are in neural network architecture for robotics systems, object detection and identification (face, vehicle, and elderly fall detection), iris recognition, learning Rules in the Purkinje cell system of the cerebellar cortex and its application to a bipedal robot.
Pierre Beauseroy
Pierre Beauseroy received his engineering degree in computer science and his master degree in complex system control from University of Technology of Compiegne in 1988. He received his PHD degree in complex system control from the same university in 1992. Since 1993 he is continuing his research at the University of Technology of Troyes. He is a full professor since 2010 and leads the system modeling and dependability team (LM2S) since 2011. His major research interests are pattern recognition and machine learning.
