Biometric Person Authentication using Fingerprints and Handwriting
Description
Fingerprint analysis is one of the most reliable and most widely accepted biometric techniques for person identification. Most automatic fingerprint identification systems use a procedure for the extraction of characteristic features followed by a feature matching algorithm. In this project we study the application of structural pattern recognition methods, in particular attributed graph matching, to the problem of fingerprint classification and identification. Our main objective includes the development of efficient fingerprint search algorithms based on the ridge line structures occurring in fingerprints.
Handwriting is believed to be unique to one writer. Writer identification is the task of determining the author of a sample of handwriting from a set of writers. Writer verification is the task of deciding whether or not a handwritten text has been written by a certain writer. In this project we investigate various approaches to writer identification and verification.
