Iris and Signature Authentication Using Continuous Dynamic Programming

Abstract

In online applications, authentication systems which are covenant with a measurable behavioral trait and physiological characteristics are essential. This paper deals with authenti- cation of an individual's on-line signature data and textual iris information using continuous dynamic programming (CDP). Instead of working on primary features such as image or on-line data, working on the derived kinematic plot is robust way of authentication. I. INTRODUCTION Signature verification and Iris recognition, as biometric technologies have great advantages such as variability, scal- ability and security thus providing a variety of applications. Secure communications for mortgage, passport, internet com- merce and mobile commerce are some of the areas which thrive on recognition for payments, logins via a tablet PC, crypto-biometrics and for bio-hashing. New recognition tech- niques that can mine and discover behavioral knowledge in large data sets are very much essential. Challenging concept of signature authentication is that, it is strongly affected by user-dependencies as it varies from one signing instance to another in a known way. The iris recognition system in an unconstrained environment due to quality of pictures, bad lighting, and occlusion by eyelids, noises and inappropriate eye positioning is still far from perfection. Research issues are based on iris localization, nonlinear normalization, occlusion segmentation, liveness detection, large scale identification. Some of the various approaches of on-line signature verifi- cation systems as reported in literature are broadly divided into four classes as global parametric feature based approach, function-based approach, hybrid methods based on both of the above stated schemes and trajectory construction methods. Feature-based approaches are statistical parametric methods in which a holistic vector representation consisting of a set of global features is derived from the signature trajectories. Function-based approaches are methods in which time se- quences describing local properties of the signature are used for recognition. Trajectory construction methods produce and control complex two-dimensional synergistic movements. Iris recognition methods are classified into phase-based method, texture-analysis based method, zero-crossing representation method, approach based on local intensity variations and approach using Independent Component Analysis(ICA). In phase-based method the iris pattern is demodulated to extract phase information using quadrature 2D Gabor wavelets (1). Texture-analysis based method uses Laplacian of Gaussian applied to the image at multiple scales (2). The zero-crossing representation method deals with the representation of features of the iris at different resolution levels based on the wavelet transform zero crossing representation (3). In the approach based on local intensity variations the sharp variation points of iris patterns are recorded as features and are utilized to represent the characteristics of the iris (4). In the approach using ICA the independent components are uncorrelated and the feature coefficients are considered to be nongaussian and mutually independent (5).