DEVELOPMENT OF AN EFFICIENT SIGNATURE VERIFICATION SYSTEM USING AN INTERVAL SYMBOLIC REPRESENTATION AND FUZZY LOGIC

Price: 4000 Naira

CHAPTER ONE

  1.  INTRODUCTION

Notwithstanding efforts toward the dematerialization of documents, the need for fast and accurate paper-based document authentication is still growing in our society. The field of biometrics is an important area of study as it offers many advantages over more commonly used authentication methods such as photo ID cards, magnetic strip cards etc. Nowadays, biometric technologies are increasingly and more frequently being used to ensure identity verification. Signatures often incorporate complex geometric patterns that make them a relatively secure means for authorization for high security environments. For historical reasons, the handwritten signature continues to be the most commonly accepted form of transaction confirmation, as well as being used in civil law contracts, acts of volition, or authenticating one’s identity. Some other signature verification applications include the authentication of bank checks, ID personal cards, administrative forms, formal agreements, acknowledgement of services received, etc. (G. F. Luger, 2005).

Signature verification has been a topic of intensive research during the past several years due to the important role it plays in numerous areas, including in financial applications. Considering the large number of signatures verified daily through visual inspection by people, the construction of a robust and accurate automatic signature verification system has many potential benefits for ensuring authenticity of signatures and reducing fraud and other crimes. The goal of an automatic signature verification system is to be able to verify the identity of an individual, based on the analysis of his or her signature through a process that discriminates a genuine signature from a forgery. (B. Jayasekara, A. Jayasiri 2006).

The verification of human signatures is particularly concerned with the improvement of the interface between human beings and computers. Depending on data acquisition mechanism, there are two methods of signature verification – Online or Dynamic and Offline or Static. Online method requires special set of devices and instruments to capture the pen movements and pressure over the paper at the same time of the writing. On the other hand, the offline approach uses an optical scanner in order to obtain a digital representation of the signature composed of M × N pixels. In offline signature verification, the signature image is considered as a discrete 2D function f(x, y), where x = 0, 1, 2… M and y = 0, 1, 2… N denotes the spatial coordinates. The value of f in any (x, y) corresponds to the grey level in that point. Processing is done on the scanned images. Efficient signature recognition is more difficult than online as dynamic information are not available and it is difficult to recover them from the offline images. But requirement of acquiring the signature on some special arrangement makes the online method unsuitable for many of the practical uses. Offline has the advantage of using it in the same way as the existing manual recognition method. (A. Zimmer and L. L. Ling, 2001).

A quick look at the literature of signature identification / verification indicates that handwritten signature identification / verification systems are well established. A wide range of algorithms have already been developed in the past few decades to automatically process handwritten signatures in various signature-based applications, such as person identification / verification, cheque fraud detection, bank transactions, and crime detection Considering the way in which the proposed methods in the literature dealt with the handwritten signatures, the methods can be categorized into two groups: a) identification, and b) verification. The identification methods decide the signature group among a number of groups that the claimed signature belongs to, and the verification methods decide acceptance or rejection of a person’s claimed signature. Three different types of forgeries (random, simple and skilled forgeries) have commonly been used in the literature .Random and simple forgery samples are generated by individuals without any knowledge about the signers and their signatures, whereas, samples of skilled forgeries are produced by people who have already seen an original instance of a signature and try to generate a copy of the original signature as close as possible to the original one. Indeed, the problem of signature verification considering skilled forgeries is a challenging task .Since data/signature collection can be performed using online and off-line mediums, the signature verification methods in the literature can consequently be grouped into on-line and off-line approaches . On-line signature verification systems generally have higher performance compared to offline signature verification systems. (S. Mozaffari, K. Faez and M. Ziaratban, 2006).

1.2 Aims and Objective of the Study

The aim of this project is to develop an efficient signature verification system using an interval symbolic representation and fuzzy logic which will be guided by the following objectives

  1. To be able to verify the identity of an individual based on the analysis of his or her signature through a process that discriminates a genuine signature from a forgery.
  2. To have potential benefits for ensuring authenticity of signatures and reducing fraud and other crimes.
  3. To improve the efficiency of the signature verification systems,
  4. To transform the original signatures using the identity
  5. To tackle the problem of detecting skilled forgeries
  6. proposed an approach based on a smoothness criterion
  7. Data capturing using PHP upload image
  8. Pre-processing using the PHP backend processor
    1. Scope of the Study

This scope of the Development Of An Efficient Signature Verification System Using An Interval Symbolic Representation And Fuzzy Logic. This section presents a histogram feature based online signature verification system that comprises of a feature extractor, a template generator and matcher. First, the input online signature is processed by the feature extractor module to extract a set of histograms from which a feature vector is computed. Then, the system constructs a user-specific template from the feature sets derived from multiple enrolment signatures. This template is later used by the matching process to compare against a query signature to verify whether it has been input by the genuine user.

1.4       Significance of the Study

This study presents a method to extract a model-free non-invertible feature set from an efficient signature. Specifically, the proposed feature set comprises of sets of histograms that capture distributions of attributes generated from several raw signature data sequences and their combinations. Benefits of the proposed method are as follows.

1. The feature set can be computed efficiently, i.e. in linear time proportional to the length of an efficient signature.

2. The features stored in the system for verification are irreversible. In other words, the original dynamic construction of an efficient signature is not revealed even when the features are revealed. This is a desirable property from a biometric privacy point of view. 3. Verification performance of the proposed system is superior to several state of the art algorithms on common data sets.

1.5 Limitation of the Study

Efficient signature verification systems generally have higher performance compared to offline signature verification systems. This is because efficient systems take into account different dynamic information such as velocity, acceleration, pressure, stroke order, force, etc. that are not available in off-line systems. Moreover, as off-line signature verification systems use statistical information determined from the signature images, the problem becomes much more complicated. Nevertheless, off-line signature verification systems are more popular as most signatures are written on papers, documents, checks, etc.

1.6       Statement of the Problem

The verification error-rates of the above mentioned systems are not too encouraging particularly for skilled forgeries. Therefore in this paper, experiments are carried out to search for more discriminative features since this will go a long way to improve the effectiveness of the proposed system. And three features are found to be highly discriminative in comparison with other extracted features; these features are used to build the proposed system. Also in previous systems, classification decisions are based on minimum, maximum distance of a test signature from the reference signatures and template distance .But in the proposed system, we developed a better method in which the threshold value is obtained based on the average of all the distances obtained from the cross-alignment of all reference signatures.  

  1. Definition of Terms
  2. RANDOM FORGERY: The forger nor has access to the genuine signature neither has any information about the author’s name. Forger reproduces a random signature.
  3. SIMPLE FORGERY: The forger has no access to the sample of the signature but he/she knows the author’s name and the forger produces the signature in his/her own style.
  4. SKILLED FORGERY: The forger has access to the samples of the genuine signature and thus he/she is able to reproduce it.
  5. FALSE REJECTION RATE: The false rejection rate (FRR) is related to genuine signatures that were rejected by the system; that is, classified as forgeries.
  6. FALSE ACCEPTANCE RATE: The false acceptance rate (FAR) is related to forgeries that were misclassified as genuine signatures
  7. IDENTIFICATION: The identification methods decide the signature group among a number of groups that the claimed signature belongs
  8. VERIFICATION: The verification methods decide acceptance or rejection of a person’s claimed signature.
  9. FUZZY LOGIC: is almost synonymous with the theory of fuzzy sets, a theory which relates to classes of objects with unsharp boundaries in which membership is a matter of degree.
  10. INTER-PERSONAL: That which is associated with different persons.
  11. INTRA-PERSONAL: That which is associated with the same person.
  12. TEST SIGNATURE: Signature submitted for authenticity verification.
  13. DISCRIMINANCY: Capability to distinguish between genuine and forged signatures.
  14. ALLOGRAPH: A letter of an alphabet in a particular shape (as A or a).
  15. BALLISTIC HANDWRITING: Handwriting characterized by a spurt of activity without incorporating feedback.
  16. SIGNATURE: is a handwritten (and often stylized) depiction of someone’s name, nickname, or even a simple “X” or other marks that a person writes on documents as a proof of identity and intent.
  17. SIGNER/SIGNATORY: The writer of a signature
  18. AUTOGRAPH: An artistic signature
  19. SIGNATURE VERIFICATION: is a technique used by banks, intelligence agencies and high profile institution to validate the identity of an individual.

Get Complete Material

Leave a Reply

Your email address will not be published. Required fields are marked *