Writer Verification by Using an Arbitrary Part of Feature Sequence Extracted from On-Line Handwritten Character/Figure Patterns Hiroshi Kameya A DISSERTATION SUBMITTED IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF DOCTOR OF PHIROSOPHY IN COMPUTERSCIENCE AND ENGINEERING

Writer Verification by Using an Arbitrary Part of Feature Sequence Extracted from On-Line Handwritten Character/Figure Patterns Hiroshi Kameya Chair of Supervisory Committee: Professor Ryuichi Oka Graduate Department of Information Systems By introducing the continuous dynamic programming (CDP) algorithm developed by Oka (1998), I have developed a new segmentation-free, text-independent biometric handwriting-based verification method (Kameya et al., 2006) improving the average correct acceptance rate and the average correct rejection rate of forgeries to a practically useful level of about 95% and 100%, respectively, outperforming the only other biometric text-independent writer verification method of Yamazaki and Komatsu (1996a,b, 1999, 2000) based on a P-type Fourier descriptor-based learning vector quantisation scheme. To implement a text-independent, DP-based biometric writer verification, my spotting-enabling CDP algorithm has not only successfully traced and tracked an optimal microscopic dynamic features of real-time writing processes of either scanned characters or images of relevant individuals but also has implemented extension to a more secure text-independent writer verification method by exploiting the built-in spotting function of the CDP method, which is capable of ignoring inputs outside the task domain. This is so because a text-independent sample can be selected from any of many possible candidates located at an arbitrary location within the specified long reference sample. I have demonstrated the applicability of the method not only to Japanese text but also to English text that tends to assess the language independence of the method.