Download presentation
Presentation is loading. Please wait.
Published bySamuel Ward Modified over 8 years ago
1
Introduction to Biometrics Dr. Bhavani Thuraisingham The University of Texas at Dallas Lecture #6 Guest Lecture + Some Topics in Biometrics September 12, 2005
2
Outline l Guest Lecture l Some Topics in Biometrics
3
Introduction to Biometrics Guest Lecture Image Feature Extraction and Annotation September 12, 2005
4
Some Topics in Biometrics l Reference - http://biometrics.cse.msu.edu/info.html http://biometrics.cse.msu.edu/info.html - Papers published on the web by researchers at Michigan State University l Overview l Fingerprint Identification l Hand Geometry l Face Location l Multi-Biometrics
5
Overview l Biometrics is the automatic identification of a person based on his/her physiological and behavioral characteristics l Verification vs. Identification - Am I whom I claim I am? - Who am I? l Applications - Criminal identification, ATMs, Cellular Phones, Smart cards, PCs, E-Commerce, Automobiles (biometrics replacing car keys)
6
Fingerprint Identification l Finger-print matching - Two categories: Minutiae based, Correlation based l Minutiae-based techniques - First find the minutiae points and then map their relative placement on the finger - Issues: difficult to extract minutiae points if fingerprinting is of low quality l Correlation-based techniques - Spatial correlation of regions - Issues: Affected by Image translation
7
Fingerprint Identification (Concluded)) l Finger-print classification - Classify the fingerprints so that search time is reduced - Form groups of fingerprints; Classification is obtained by matching with pre-specified types of finger-prints - When a new finger-print arrives try and place it into a group - Classification based data mining/machine learning algorithms such as K-Nearest Neighbor l Fingerprint Image Enhancement - Algorithms to enhance the finger-print - This is expected to facilitate finger-print matching - Makes it less difficult to extract minutiae from fingerprints
8
Hand Geometry l Uses geometric shape of hand for authenticating user’s identity - Combine various individual features of hand for effective verification l Human hand is not in general unique (not the case with fingerprints) l Reason one may want to use hands instead of finger-prints is to ensure privacy l Some pros and cons - Hand geometry gives better privacy - But hand geometry is not unique; therefore may be used for verification - Not suitable for identification
9
Face Location and Retrieval l Problem - Given an arbitrary black and white still image, find the location and size of every human face it contains l Applications - First step in automatic face recognition - Image database indexing - Search by content for surveillance systems
10
Multi-Biometrics l Integrating Faces and Fingerprints for Identification - Single biometric may not be effective - Integrate multiple biometrics such as fingerprints and faces l Fingerprint, Face and Speech - Better to use a third biometric and that is speech l Challenge - What is an effective combination of biometrics?
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.