In this research we evaluate the use of GLRLM features in offline handwritten signature verification. For each known writer we take a sample of fifteen genuine signatures and extract their GLRLM descriptors. We also used some forged signatures to test the efficiency of our system.
We calculate the simple statistical measures and also inter- and intra-class Euclidean distances (measure of variability within the same author) among GLRLM descriptors of the known signatures. The key points Euclidean distances, the image distances and the intra class thresholds are stored as templates.
We evaluate use of various intra-class distance thresholds like the mean, standard deviation and range. For each signature claimed to be of the known writers, we extract its GLRLM descriptors and calculate the inter-class distances, that is the Euclidean distances between each of its GLRLM descriptors and those of the known template and image distances between the test signature and members of the genuine sample. The intra-class threshold is compared to the inter-class threshold for the claimed signature to be considered a forgery. A database of 525 genuine signatures and 30 forged signatures consisting of a training set and a test set are used.
Table of Contents
1. Introduction
1. Introduction
1.2 Problem Motivation
1.3 Biometrics Introduction
1.3.1 Past
1.3.2 Present
1.3.3 Future
1.4 Personal Biometric Criteria
1.5 Biometric System-Level Criteria
1.6 Performance parameters
1.7 Thesis outline
2. Introduction to Signature Verification
2. Introduction
2.1 Pattern recognition
2.2 Feature extraction
2.3 Handwritten signatures
2.3.1 On-line and off-line signatures
2.4 Forgery types
2.4.1 Random forgeries
2.4.2 Simple forgeries
2.4.3 Skilled forgeries
2.5 Writer-dependent and writer-independent verification
2.6 Objectives
3. Literature survey
3.1 Texture Analysis
3.1.1Inspection
3.1.2 Medical Image Analysis
3.2 Signature verification
3.3 Gray level run length encoding
4. Problem Definition and Methodology
4. Introduction
4.1 Problem Definition
4.2 Steps Involved
4.2.1Signature enrolment
4.2.2 Obtaining region of interest
4.2.3 Feature extraction
4.2.4 Definition of the Run-Length Matrices
4.2.5 Calculation of Euclidean Distances
4.2.6 Creation of the known signature template.
4.2.7 Signature Verification
4.3 Measurement of the Signature Verifier Accuracy
4.4 Proposed Algorithm using Euclidean distance
5. Experiment and Results
5. Introduction
The simple statistical approach :
5.1.1 Examples of verified signatures:
5.2 Euclidean distance model
5.2.1 Threshold
6. Conclusion
6.1 Conclusion
7. Future work
7.1 Future work
Objectives and Topics
The main objective of this research is to develop an efficient and economically viable offline handwritten signature verification system using a novel feature extraction technique based on Gray Level Run Length Matrix (GLRLM) analysis. The study aims to achieve robust signature verification by converting raw monochrome signature images into feature vector representations and comparing them using Euclidean distance measures.
- Implementation of a novel feature extraction technique utilizing GLRLM.
- Development of a robust off-line signature verification system.
- Evaluation of signature verification performance using statistical measures (FAR/FRR).
- Investigation of Euclidean distance models for comparing signature patterns.
Excerpt from the book
4.2.4 Definition of the Run-Length Matrices
With the observation that, in a coarse texture, relatively long gray level runs would occur more often and that a fine texture should contain primarily short runs, Galloway proposed the use of a run length matrix for texture feature extraction . The GLRLM is based on computing the number of gray-level runs of various lengths. A gray level run is a set of consecutive and collinear pixel points having the same gray level value. The length of the run is the number of pixel points in the run . The Gray Level Run Length matrix is constructed as follows:
R(θ) = ( g (i,j) | θ ), 0 ≤ I ≤ Ng , 0 ≤ I ≤ Rmax;
where Ng is the maximum gray level and Rmax is the maximum length. Let p (i, j) be the number of times there is a run of length j having gray level i. There are five Run Length Matrix based features computed for 4 directions of run (0°, 45°, 90° , 135° , {0°, 45°, 90° , 135° } run). I=1, …, Ng and j=1, …, Nr.
Summary of Chapters
Chapter 1: Provides an introduction to information security and biometric authentication, motivating the need for offline signature verification.
Chapter 2: Discusses the field of signature verification, including pattern recognition, forgery types, and the differences between writer-dependent and writer-independent verification.
Chapter 3: Reviews literature on texture analysis and various existing signature verification techniques.
Chapter 4: Defines the problem and details the methodology, specifically the implementation of GLRLM and the Euclidean distance approach for signature verification.
Chapter 5: Presents the experimental results, including the simple statistical approach and the performance statistics of the proposed system.
Chapter 6: Offers concluding remarks on the complexity and effectiveness of the developed system.
Chapter 7: Discusses potential future work, including the investigation of other distance measures and classification techniques.
Keywords
Handwritten Signature Verification, GLRLM, Texture Analysis, Biometrics, Euclidean Distance, Forgery Detection, Pattern Recognition, Feature Extraction, Long Run Emphasis, FAR, FRR, Offline Signature Verification, Image Processing, Statistical Approach, Signature Enrolment
Frequently Asked Questions
What is the core focus of this research?
The research focuses on implementing a novel feature extraction technique for offline handwritten signature verification using Gray Level Run Length Matrix (GLRLM) analysis to improve security.
What are the primary thematic fields covered?
The work covers biometrics, texture analysis, pattern recognition, and signature verification methodologies.
What is the primary objective of the thesis?
The objective is to successfully design and implement a novel feature extraction technique using the GLRLM method and a robust off-line signature verification system using distance classifiers.
Which scientific methodology is utilized?
The research employs a texture-based approach where signature images are converted into 2D arrays, followed by GLRLM feature extraction and verification via Euclidean distance measurements.
What does the main body of the work address?
It addresses the literature survey on texture analysis, the detailed algorithm steps for signature enrolment and verification, and experimental results obtained from the dataset.
Which keywords best characterize this work?
The work is characterized by terms such as offline signature verification, GLRLM, texture analysis, Euclidean distance, and biometric authentication.
How is the GLRLM used to define signature textures?
GLRLM computes the number of gray-level runs of various lengths in an image, helping to differentiate between coarse and fine textures within a signature.
Why are Euclidean distances used in this system?
Euclidean distance is used to measure the variability between signature images, providing a distance-based metric to determine whether a test signature matches a genuine template.
- Quote paper
- Saba Mushtaq (Author), 2012, Signature verification based on a feature extraction technique, Munich, GRIN Verlag, https://www.grin.com/document/376136
