International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 06 Issue: 02 | Feb 2019 www.irjet.net p-ISSN: 2395-0072 © 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 1248 A Trailblazing Intrigue Applying Ordinal Analysis of Iris Pattern for Invincibility S. Sheeba Jeya Sophia 1 1 Assistant Professor, Department of Electronics & Communication Engineering, Vaigai College of Engineering, Madurai, Tamil Nadu ----------------------------------------------------------------------***--------------------------------------------------------------------- Abstract - Iris recognition is a biometric that depends on the uniqueness of the iris. Iris Recognition is regarded as the most reliable and accurate biometric identification system available. Elements of a person's biometrics are typically stable over the duration of a lifetime, and thus, it is highly important to protect biometric data while supporting recognition. A recognition system based on iris has become important in the last decades due to its reliability and comfort. Images of a human iris contain rich texture information useful for identity authentication. A key and still open issue in iris recognition is how best to represent such textural information using a compact set of features (iris features). In this paper, we propose using ordinal measures for iris patterns with the objective to characterize qualitative relationship between iris regions rather than precise measurements of iris image structures. Such a representation may lose some image- specific information, but it achieves a good trade-off between distinctiveness and robustness. Key Words: Biometrics, Iris Recognition, Bi-section methods, Ordinal Measures, Circular Symmetric Filter, Hamming Distance 1. INTRODUCTION In recent years, the security of biometric data has been widely studied. Biometric data are believed to be unique for every person and the primary data of the biometric data remains invariable over the entire lifetime of a person [1]. It employs physiological or behavioral characteristics to identify an individual. The physiological characteristics are iris, fingerprint, face and hand geometry. Voice, signature and keystroke dynamics are classified as behavioral characteristics [2]. Among this iris recognition is believed to have reliability and accuracy. Iris recognition is a new way to identify iris images and identify identities through specific algorithms. Because of its high accuracy, uniqueness, fast speed and convenient acquisition, non-invasion and so on [3]. RIS recognition, as an extremely reliable method for identity authentication, is playing a more and more important role in many mission-critical applications, such as assess control, national ID card, border crossing, welfare distribution, missing children identification, etc. The uniqueness of iris pattern comes from the richness of texture details in iris images, such as freckles, coronas, crypts, furrows, etc [4]. Most iris recognition systems consist of four stages: image acquisition, iris segmentation, iris normalization and recognition [5]. IRIS codes are acknowledged to be uncorrelated not only between unrelated persons, but also even between identical twins and between the left and right irises of the same person [1]. Matching the iris codes from the left and right eyes of the same person gives a result that is on average basically the same as matching iris codes from unrelated persons [6]. The most challenging issue in iris feature representation is to achieve sensitivity to interclass differences and at the same time to maintain robustness against intra-class variations. So, a most important question one may ask is “What are the intrinsic and robust features of iris patterns?” or in practice, “How do we computationally model iris texture effectively and efficiently?” An equally important question to ask is “Do the currently best performing iris recognition algorithms have anything in common and what makes them effective? [4]. In this paper, we introduce ordinal measures for iris image representation in an attempt to answer some of these questions. Ordinal measures encode qualitative information of visual signal rather than its quantitative values.Paper is organized as follows. Section 2 describes latest methods used in iris recognition and its applications. The work and methodologies proposed are given in Section 3. Section 4 presents experimental results showing results of images tested. Finally, Section 5 presents conclusion & future enhancement of the works planned. 2. RELATED WORK Daugman proposed the first successful algorithm for iris recognition [7]. In this algorithm, even and odd Gabor filters are proposed to demodulate phase information in each iris region. Then, phase value is coarsely quantized to 2-bit binary codes, and a given iris image is represented with 256 Bytes iris code. At the feature-matching step, the dissimilarity between two iris codes is measured by Hamming distance. Daugman’s algorithm [7], [8] has been widely used in commercial iris recognition products. Other iris representation methods include emergent frequency and instantaneous phase [9], local texture energy orientation [10], Haar wavelet frame decomposition [11], multiscale zero-crossing representation [12], normalized directional energy feature [13], Haar wavelet binary features [14],