THEORETICAL ADVANCES Automated personal identification system based on human iris analysis R. T. Al-Zubi Æ D. I. Abu-Al-Nadi Received: 4 September 2005 / Accepted: 7 October 2006 / Published online: 29 November 2006 Ó Springer-Verlag London Limited 2006 Abstract In general, a typical iris recognition system includes iris imaging, iris liveness detection, iris image quality assessment, and iris recognition. This paper presents an algorithm focusing on the last two steps. The novelty of this algorithm includes improving the speed and accuracy of the iris segmentation process, assessing the iris image quality such that only the clear images are accepted so as to reduce the recognition error, and producing a feature vector with discrimi- nating texture features and a proper dimensionality so as to improve the recognition accuracy and computa- tional efficiency. The Hough transform, polynomial fitting technique, and some morphological operations are used for the segmentation process. The phase data from 1D Log-Gabor filter is extracted and encoded efficiently to produce a proper feature vector. Experi- mental tests were performed using CASIA iris data- base (756 samples). These tests prove that the proposed algorithm has an encouraging performance. Keywords Personal identification  Human iris  1D Log-Gabor filter  Template matching 1 Introduction Personal identification is not a new topic, but its methods are changing according to the human activity requirements and the development of information technology. There are traditional methods for personal identification such as physical key, personal identifi- cation number (PIN), and a secret password. These methods suffer from various problems; for example, it can be lost, forgotten, or guessed. Today one of the important human activity requirements is a fast, reli- able, and automatic personal identification system. Methods based on biometric measurements, such as fingerprints, voiceprints, hand written signature, hand shape, palm-print, and hand thermogram had been proposed [1]. Unfortunately, these methods can be invasive; typically, the operator is required to make physical contact with a sensing device or otherwise take some special action as reciting a specific phonemic sequence. One possible alternative to these methods that has the potential to be less invasive is automated face recognition [1]. But in face recognition, difficulties arise from the fact that the face is a changeable social organ displaying a variety of expressions, as well as being an active three-dimensional (3D) object whose image varies with viewing angle, illumination, and age. Automated iris recognition is one of the most reli- able biometrics [2]. Interestingly, the spatial patterns that are apparent in the human iris are highly distinc- tive to an individual [2–6]. Furthermore, the iris is an overt body that is available for remote assessment. All these desirable properties make iris recognition one of the top security solutions. In general, a typical personal identification system, which is based on iris analysis, consists of four stages: iris image acquisition, iris liveness detection, iris image quality assessment, and iris recognition. In iris image acquisition, capturing a high quality iris image for recognition is one of the major challenges of auto- mated iris recognition in practical applications. To realize this challenge, consider some technical issues R. T. Al-Zubi  D. I. Abu-Al-Nadi (&) Electrical Engineering Department, University of Jordan, Amman, Jordan e-mail: dnadi@ju.edu.jo 123 Pattern Anal Applic (2007) 10:147–164 DOI 10.1007/s10044-006-0058-2