CBM340 Biometric Systems Syllabus:
CBM340 Biometric Systems Syllabus – Anna University Regulation 2021
COURSE OBJECTIVES:
To Study about:
• To introduce the relevance of this course to the existing technology through demonstrations, case studies, simulations, contributions of scientist, national/international policies with a futuristic vision along with socio-economic impact and issues.
• To understand the general principles of design of biometric systems and the underlying trade-offs.
• To study the technologies of fingerprint, iris, face and speech recognition.
• To study of evaluation of biometrics systems.
UNIT I INTRODUCTION TO BIOMETRICS
Introduction and back ground – biometric technologies – passive biometrics – active biometrics – Biometric characteristics, Biometric applications – Biometric Authentication systems- Taxonomy of Application Environment, Accuracy in Biometric Systems- False match rate- False non match rate Failure to enroll rate- Derived metrics-Biometrics and Privacy.
UNIT II FINGERPRINT TECHNOLOGY
History of fingerprint pattern recognition – General description of fingerprints- fingerprint sensors, fingerprint enhancement, Feature Extraction- Ridge orientation, ridge frequency, fingerprint matching techniques- correlation based, Minutiae based, Ridge feature based, fingerprint classification, Applications of fingerprints, Finger scan- strengths and weaknesses, Evaluation of fingerprint verification algorithms.
UNIT III FACE RECOGNITION AND HAND GEOMETRY
Introduction to face recognition, face recognition using PCA, LDA, face recognition using shape and texture, face detection in color images, 3D model based face recognition in video images, Neural networks for face recognition, Hand geometry – scanning – Feature Extraction – classification.
UNIT IV IRIS RECOGNITION
Introduction, Anatomical and Physiological underpinnings, Iris sensor, Iris representation and localization- Daugman and Wilde‘s approach, Iris matching, Iris scan strengths and Weaknesses, System performance, future directions.
UNIT V VOICE SCAN AND MULTIMODAL BIOMETRICS
Voice scan, speaker features, short term spectral feature extraction, Mel frequency cepstral coefficients, speaker matching, Gaussian mixture model, NIST speaker Recognition Evaluation Program, Introduction to multimodal biometric system – Integration strategies – Architecture – level of fusion – combination strategy, examples of multimodal biometric systems, Securing and trusting a biometric transaction – matching location – local host – authentication server – match on card (MOC).
COURSE OUTCOMES:
On successful completion of this course, the student will be able to
CO1: Demonstrate the principles of biometric systems.
CO2: Develop fingerprint recognition technique.
CO3: Design face recognition and hand geometry system.
CO4: Design iris recognition system.
CO5: Develop speech recognition and multimodal biometric systems.
TOTAL:45 PERIODS
TEXT BOOKS
1. James Wayman& Anil Jain, “Biometric Systems- Technology Design and Performance Evaluation”, SPRINGER (SIE), 1st Edition, 2011
2. Paul Reid, “Biometrics for Network Security”, Pearson Education, 2004
3. S.Y. Kung, S.H. Lin, M.W., “Biometric Authentication: A Machine Learning Approach”, Prentice Hall, 2004
REFERENCES
1. Nalini K Ratha, Ruud Bolle, “Automatic fingerprint recognition system’’, Springer, 2003.
2. L C Jain, I Hayashi, S B Lee, U Halici, “Intelligent Biometric Techniques in Fingerprint and Face Recognition”, CRC Press, 1st Edition, 1999.
3. John Chirillo, Scott Blaul, “Implementing Biometric Security”, John Wiley & Sons, 2003.