ABSTRACT
In this work we describe a new approach to dynamic signature verification using the discriminative training framework. The authentic and forgery samples are represented by two separate Gaussian Mixture models and discriminative training is used to achieve optimal separation between the two models. An enrollment sample clustering and screening procedure is described which improves the robustness of the system. We also introduce a method to estimate and apply subject norms representing the "typical": variation of the subject's signatures. The subject norm functions are parameterized, and the parameters are trained as an integral part of the discriminative training. The system was evaluated using 480 authentic signature samples and 260 skilled forgery samples from 44 accounts and achieved an equal error rate of 2.25%.
TABLE OF CONTENT
TITLE PAGE
CERTIFICATION
APPROVAL
DEDICATION
ACKNOWLEDGEMENT
ABSTRACT
TABLE OF CONTENT
CHAPTER ONE
1.0INTRODUCTION
1.1STATEMENT OF PROBLEM
1.2PURPOSE OF STUDY
1.3AIMS AND OBJECTIVES
1.4SCOPE/DELIMITATIONS
1.5LIMITATIONS/CONSTRAINTS
1.6DEFINITION OF TERMS
CHAPTER TWO
2.0LITERATURE REVIEW
CHAPTER THREE
3.0METHODS FOR FACT FINDING AND DETAILED DISCUSSIONS OF THE SYSTEM
3.1 METHODOLOGIES FOR FACT-FINDING
3.2DISCUSSIONS
CHAPTER FOUR
4.0FUTURES, IMPLICATIONS AND CHALLENGES OF THE SYSTEM
4.1FUTURES
4.2IMPLICATIONS
4.3CHALLENGES
CHAPTER FIVE
5.0SUMMARY, RECOMMENDATIONS AND CONCLUSION
5.1SUMMARY
5.2RECOMMENDATION
5.3CONCLUSION
REFERENCES