BIOMETRIC SYSTEMS, DESIGN AND APPLICATIONS Edited by Zahid Riaz Biometric Systems, Design and Applications Edited by Zahid Riaz Published by InTech Janeza Trdine 9, 51000 Rijeka, Croatia Copyright © 2011 InTech All chapters are Open Access articles distributed under the Creative Commons Non Commercial Share Alike Attribution 3.0 license, which permits to copy, distribute, transmit, and adapt the work in any medium, so long as the original work is properly cited. After this work has been published by InTech, authors have the right to republish it, in whole or part, in any publication of which they are the author, and to make other personal use of the work. Any republication, referencing or personal use of the work must explicitly identify the original source. Statements and opinions expressed in the chapters are these of the individual contributors and not necessarily those of the editors or publisher. No responsibility is accepted for the accuracy of information contained in the published articles. The publisher assumes no responsibility for any damage or injury to persons or property arising out of the use of any materials, instructions, methods or ideas contained in the book. Publishing Process Manager Mirna Cvijic Technical Editor Teodora Smiljanic Cover Designer Jan Hyrat Image Copyright lavitrei, 2011. Used under license from Shutterstock.com First published September, 2011 Printed in Croatia A free online edition of this book is available at www.intechopen.com Additional hard copies can be obtained from orders@intechweb.org Biometric Systems, Design and Applications, Edited by Zahid Riaz p. cm. ISBN 978-953-307-542-6 free online editions of InTech Books and Journals can be found at www.intechopen.com Contents Preface IX Part 1 Fingerprints Verification and Identification 1 Chapter 1 Reliability of Fingerprint Biometry (Weibull Approach) 3 Robert Brumnik, Iztok Podbregar and Teodora Ivanuša Chapter 2 Finger-Vein Recognition Based on Gabor Features 17 Jinfeng Yang, Yihua Shi and Renbiao Wu Chapter 3 Efficient Fingerprint Recognition Through Improvement of Feature Level Clustering, Indexing and Matching Using Discrete Cosine Transform 33 D. Indradevi Part 2 Face Recognition 55 Chapter 4 Facial Identification Based on Transform Domains for Images and Videos 57 Carlos M. Travieso-González, Marcos del Pozo-Baños and Jesús B. Alonso Chapter 5 Towards Unconstrained Face Recognition Using 3D Face Model 77 Zahid Riaz, M. Saquib Sarfraz and Michael Beetz Chapter 6 Digital Signature: A Novel Adaptative Image Segmentation Approach 93 David Freire-Obregón, Modesto Castrillón-Santana and Oscar Déniz-Suárez Part 3 Iris Segmentation and Identification 109 VI Contents Chapter 7 Solutions for Iris Segmentation 111 Milena Bueno Pereira Carneiro, Antônio Cláudio P. Veiga, Edna Lúcia Flôres and Gilberto A. Carrijo Chapter 8 Detecting Cholesterol Presence with Iris Recognition Algorithm 129 Ridza Azri Ramlee, Khairul Azha and Ranjit Singh Sarban Singh Chapter 9 Robust Feature Extraction and Iris Recognition for Biometric Personal Identification 149 Rahib Hidayat Abiyev and Kemal Ihsan Kilic Chapter 10 Iris Recognition System Using Support Vector Machines 169 Hasimah Ali and Momoh J. E. Salami Part 4 Other Biometrics 183 Chapter 11 Verification of the Effectiveness of Blended Learning in Teaching Performance Skills for Simultaneous Singing and Piano Playing 185 Katsuko T. Nakahira, Yukiko Fukami and Miki Akahane Chapter 12 Portable Biometric System of High Sensitivity Absorption Detection 195 Der Chin Chen Chapter 13 Texture Analysis for Off-Line Signature Verification 219 Jesus F. Vargas and Miguel E. Ferrer Chapter 14 Design and Evaluation of a Pressure Based Typing Biometric Authentication System 235 Momoh J. E. Salami, Wasil Eltahir and Hashimah Ali Preface Biometric authentication has been widely used for access control and security systems over the past few years. It is the study of the physiological (biometric) and behavioral (soft-biometric) traits of humans which are required to classify them. A general biometric system consists of different modules including single or multi-sensor data acquisition, enrollment, feature extraction and classification. A person can be identified on the basis of different physiological traits like fingerprints, live scans, faces, iris, hand geometry, gait, ear pattern and thermal signature etc. Behavioral or soft-biometric attributes could be helpful in classifying different persons however they have less discrimination power as compared to biometric attributes. For instance, facial expression recognition, height, gender etc. The choice of a biometric feature can be made on the basis of different factors like reliability, universality, uniqueness, non- intrusiveness and its discrimination power depending upon its application. Besides conventional applications of the biometrics in security systems, access and documentation control, different emerging applications of these systems have been discussed in this book. These applications include Human Robot Interaction (HRI), behavior in online learning and medical applications like finding cholesterol level in iris pattern. The purpose of this book is to provide the readers with life cycle of different biometric authentication systems from their design and development to qualification and final application. The major systems discussed in this book include fingerprint identification, face recognition, iris segmentation and classification, signature verification and other miscellaneous systems which describe management policies of biometrics, reliability measures, pressure based typing and signature verification, bio-chemical systems and behavioral characteristics. Over the past few years, a major part of the revenue collected from the biometric industry is obtained from fingerprint identification systems and Automatic Fingerprint Identification Systems (AFIS) due to their reliability, collectability and application in document classification (e.g. biometric passports and identity cards). Section I provides details about the development of fingerprint identification and verification system and a new approach called finger-vein recognition which studies the vein patterns in the fingers. Finger-vein identification system has immunity to counterfeit, active liveliness, user friendliness and permanence over the conventional fingerprints identification systems. Fingerprints are easy to spoof however current approaches like liveliness detection and finger-vein pattern identification can easily X Preface cope with such challenges. Moreover, reliability measure of fingerprint systems using Weibull approach is described in detail. Human faces are preferred over the other biometric systems due to their non-intrusive nature and applications at different public places for biometric and soft-biometric classification. Section II of the book describes detailed study on the segmentation, recognition and modeling of the human faces. A stand-alone system for 3D human face modeling from a single image has been developed in detail. This system is applied to HRI applications. The model parameters from a single face image contain identity, facial expressions, gender, age and ethnical information of the person and therefore can be applied to different public places for interactive applications. Moreover face identification in images and videos is studied using transform domains which include subspace learning methods like PCA, ICA and LDA and transforms like wavelet and cosine transforms. The features extracted from these methods are comparatively studied by using different standard classifiers. A novel approach towards face segmentation in cluttered backgrounds has also been described which provides an image descriptor based on self-similarities which captures the general structure of an image. Current iris patterns recognition systems are reliable but collectability is the major challenge for them. A thorough study along with design and development of iris recognition systems has been provided in section III of this book. Image segmentation, normalization, feature extraction and classification stages are studied in detail. Besides conventional iris recognition systems, this section provides medical application to find presence of cholesterol level in iris pattern. Finally, the last section of the book provides different biometric and soft-biometric systems. This provides management policies of the biometric systems, signature verification, pressure based system which uses signature and keyboard typing, behavior analysis of simultaneous singing and piano playing application for students of different categories and design of a portable biometric system that can measure the amount of absorption of the visible collimated beam that passes by the sample to know the absorbance of the sample. In summary, this book provides the students and the researchers with different approaches to develop biometric authentication systems and at the same time provides state-of-the-art approaches in their design and development. The approaches have been thoroughly tested on standard databases and in real world applications. Zahid Riaz Research Fellow Faculty of Informatics Technical University of Munich Garching, Germany [...]... process A secure personal ID system must be designed to address government and business policy issues and individual privacy concerns The ID system must be secure, provide fast and effective verification of an individual’s identity, and protect the privacy of the individual’s identity information 6 Biometric Systems, Design and Applications circumstances Reliability, by definition, is probability (capability)... practical use and data safety Not only do usability improvements lead to better, easier-to-use products, they also lead to improved user 16 Biometric Systems, Design and Applications performance and satisfaction as well as substantial cost savings By designing a biometric system with usability in mind, development teams can enhance ease of use, reduce system complexity, improve user performance and satisfaction,... denoted by rk ) of the distal interphalangeal joint, as displayed in Fig 3(c): rk = arg max (Φ i ); i ∈[1,h ] (2) 20 Biometric Systems, Design and Applications Will-be-set -by- IN-TECH 4 • Three exemplar points P1 , P2 , and P0 are located along the detected baseline The points P1 and P2 represent the intersection of the joint baseline and the finger borders, respectively Meanwhile, the point P0 stands for... Efficiency and reliability are important factors in the reading and operation of biometric systems The research focuses on the measurement of activity in the process of the fingerprint biometric system, and explains what is meant by the result achieved The research we refer to reviews relevant standards, which are necessary to determine the policy of biometric measures and security mechanisms, and to successfully... likelihood of failure of a biometric card reader (airports, local government units, police stations, etc.) To increase the reliability of the biometric system and ensure the continuous operation despite the failure, we can associate two equivalent unit biometric module dynamic readings in the event of termination of the first reader to function by another 14 Biometric Systems, Design and Applications reader... unique identity Some biometric systems include the characteristics of: fingerprints, hand geometry, voice, iris, etc., and can be used for identification Most biometric systems are based on the collection and comparison of biometric characteristics which can provide identification This study begins with a historical review of biometric and radio frequency identification (RFID) methods and research areas... analysis 4.1 Even Gabor filter design Gabor filters have been successfully employed in a wide range of image-analysis applications since they are tunable in scale and orientation (Jie et al., 2007; Ma et al., 2003; Jain et al., 2007; Laadjel et al., 2008; Lee, 1996; Yang et al., 2003; Zhu et al., 2007) Considering the variations 22 Biometric Systems, Design and Applications Will-be-set -by- IN-TECH 6 (a) (b) (c)... The CIF provides a standard way for organizations to present and report quantitative data gathered in a usability test, so that it can later be compared to the results gathered in subsequent tests A review of the literature and standards for design and anthropometric measurements provided guidance on proper angles for fingers or palm placement Standards focus on line of sight and reach envelopes including... Biometric Systems, Design and Applications Assuming that the times to failure in Tables 2 are exponentially distributed couples (ti, Fi) We join them together and rank them in Table 4 and estimate parameters β and η for a biometric system with the software Weibull++7 Time to first failure is β = 4.6 and η = 72, while they are behind the times to failure of another parameter β = 3.23 and η = 117.2 For the... and to successfully implement a quality identification system The hypothesis, we have assumed in the thesis to the survey has been fully confirmed Biometric methods based on research parameters are both more reliable and effective than RFID identification systems while enabling a greater flow of people 4 Biometric Systems, Design and Applications 2 Theoretical overview Personal identification is a means . BIOMETRIC SYSTEMS, DESIGN AND APPLICATIONS Edited by Zahid Riaz Biometric Systems, Design and Applications Edited by Zahid Riaz Published by InTech. orders@intechweb.org Biometric Systems, Design and Applications, Edited by Zahid Riaz p. cm. ISBN 978-953-307-542-6 free online editions of InTech Books and Journals can be found. individual’s identity, and protect the privacy of the individual’s identity information. Biometric Systems, Design and Applications 6 circumstances. Reliability, by definition, is probability