Biometric methods for authenticating and identifying people are increasingly used in both the commercial and private sector. Today’s commercially available biometric systems show good reliability. However, they generally lack user acceptance. Users showed an antipathy towards touching a possibly dirty fingerprint scanner, or looking into an iris scanner that might malfunction and eventually impair their vision. Whether those fears are well founded or not is less important. The fact is, they have considerable influence on user acceptance. And user consent is important for a good and successful application of a biometric system, as well as for good recognition rates.
In response to the increasing demand for reliable as well as user friendly biometric systems, this work investigates the applicability of palmprint and FKP were the biometric features for authentication. Using palmprint or FKP as a biometric system avoids such problems as shown before, since it requires no subject interaction.
The main objectives of the thesis are: to propose the transform based techniques that is used to achieve higher recognition accuracy and lower equal error rate; and to examine the performance of the proposed techniques with the existing methodologies.
Table of Contents
1 INTRODUCTION TO BIOMETRICS
1.1 INTRODUCTION
1.1.1 Biometric Systems
1.2 PALMPRINT BIOMETRICS
1.2.1 Preprocessing and ROI Extraction for Palmprint Biometrics
1.3 FINGER KNUCKLE- PRINT BIOMETRICS
1.3.1 Finger Knuckle-Print Anatomy
1.3.2 Preprocessing and ROI Extraction for Finger Knuckle-Print Biometrics
1.4 PROS OF FINGER KNUCKLE-PRINT AND PALMPRINT
1.5 LOCAL AND GLOBAL FEATURES
1.6 PROBLEM STATEMENT
1.7 MOTIVATION
1.8 OBJECTIVES
1.9 BIOMETRIC DATASETS
1.9.1 College of Engineering – Pune (COEP) Palmprint Datasets
1.9.2 The PolyU Palmprint Datasets
1.9.3 Indian Institute of Technology (IIT Delhi) Touchless Palmprint Datasets
1.9.4 The PolyU Finger Knuckle-print Datasets
1.10 PERFORMANCE METRICS
1.10.1 False Acceptance Rate and False Rejection Rate
1.10.2 Speed
1.10.3 Equal Error Rate (EER)
1.10.4 Correct Classification Rate (CCR)
1.10.5 Data Presentation Curves
1.10.5.1 Receiver Operating Characteristic (ROC) Curve
2 LOCAL AND GLOBAL FEATURE EXTRACTION USING WINDOW WIDTH OPTIMIZED STOCKWELL TRANSFORM IN PALMPRINT BIOMETRIC SYSTEM
2.1 OVERVIEW OF WINDOW WIDTH OPTIMIZED S-TRANSFORM
2.1.1 Algorithm for Determining the Time Invariant p
2.1.2 Algorithm for Determining p(t)
2.1.3 Inverse of the WWOST
2.2 LOCAL - GLOBAL FEATURE EXTRACTION AND MATCHING
2.2.1 Local Feature
2.2.2 Global Feature
2.2.2.1 Phase-only correlation
2.2.2.2 Band-limited phase-only correlation
2.3 LOCAL GLOBAL FEATURE FUSION FOR PALMPRINT RECOGNITION
2.4 EXPERIMENTAL RESULTS AND DISCUSSION
2.5 SUMMARY
3 CONCLUSIONS
3.1 SUMMARY AND CONCLUSIONS
Research Objectives and Focus Areas
The primary research objective of this work is to develop and evaluate advanced transform-based techniques for palmprint and finger knuckle-print (FKP) authentication to improve recognition accuracy while reducing the equal error rate. By utilizing Window Width Optimized Stockwell Transform (WWOST) to extract both local and global features, the study aims to overcome the limitations of traditional subspace analysis methods in capturing distinctive surface features.
- Development of WWOST-based feature extraction for enhanced time-frequency representation.
- Integration of local and global feature fusion to improve authentication performance.
- Application of phase-only correlation (POC) and band-limited phase-only correlation (BLPOC) for matching.
- Performance evaluation using multiple public biometric datasets (PolyU, COEP, IIT Delhi).
- Comparative analysis against established schemes like Palm code and Ordinal Code.
Excerpt from the Book
1.2 Palmprint Biometrics
Palmprint verification is implemented in different way compared to the fingerprint technology. The optical readers used in fingerprint technology are used in palmprint scanning. The size of the palmprint scanner is bigger. It has a limiting factor when used in workstations or mobile devices. The palms of the human hands contain pattern of ridges and valleys much like the fingerprints. The region of the palm is greatly higher than the region of a finger. Therefore palmprints are more distinctive than the fingerprints. The palmprint scanner is used to capture the large area of the palm. The low resolution scanner is used to capture the additional distinctive features such as principal lines and wrinkles in the palmprint. It is very cheap. Finally, it is used to capture all the features of the palmprint such as hand geometry, ridge and valley features (e.g., minutiae and singular points such as deltas), principal lines, and wrinkles.
Palmprint recognition inherently implements many of the same matching characteristics that have allowed fingerprint recognition to be one of the most well-known and best publicized biometrics. Both palm and finger biometrics is represented by the information presented in a friction ridge imprint. The palms and fingerprints are used as a trusted form of identification for more than a century. The image captured from the palm region of the hand refers to the palmprint. The image captured from a scanner or Charge Coupled Device (CCD) is known as online image. The image taken with the help of ink and paper are known as offline image. The palm itself consists of principal lines, wrinkles (secondary lines) and epidermal ridges. The palmprint features are different from fingerprint features. The palmprint also contains other features such as indents and marks. These features are used to compare one palm with another palm. Palmprints are used for illegal, pathological, or profitable applications.
Summary of Chapters
1 INTRODUCTION TO BIOMETRICS: This chapter provides an overview of biometric authentication, detailing palmprint and finger knuckle-print biometrics, their extraction processes, and key performance metrics.
2 LOCAL AND GLOBAL FEATURE EXTRACTION USING WINDOW WIDTH OPTIMIZED STOCKWELL TRANSFORM IN PALMPRINT BIOMETRIC SYSTEM: This chapter details the core methodology using WWOST to extract local features and Fourier transforms for global features, followed by a fusion strategy for improved matching accuracy.
3 CONCLUSIONS: This chapter summarizes the research findings, confirming that the proposed transform-based WWOST system provides significantly higher recognition accuracy and lower error rates than existing methods.
Keywords
Biometrics, Palmprint, Finger Knuckle-Print, Window Width Optimized Stockwell Transform, WWOST, Feature Extraction, Local Features, Global Features, Phase-only correlation, BLPOC, Authentication, Verification, Recognition Accuracy, Equal Error Rate, Biometric Datasets
Frequently Asked Questions
What is the fundamental focus of this research?
The work focuses on enhancing biometric authentication systems using palmprints and finger knuckle-prints through a novel application of Window Width Optimized Stockwell Transform (WWOST).
What are the primary themes covered in this study?
The core themes include biometric signal analysis, transform-based feature extraction (local and global), feature fusion strategies, and performance benchmarking on standard datasets.
What is the primary objective of the proposed biometric system?
The primary goal is to achieve higher recognition accuracy and lower equal error rates (EER) compared to traditional palmprint and FKP identification methods.
Which scientific methodology is primarily employed?
The research employs the Window Width Optimized Stockwell Transform (WWOST) for time-frequency representation and feature extraction, combined with Phase-Only Correlation (POC) and Band-Limited Phase-Only Correlation (BLPOC) for matching.
What is the scope of the main chapters?
The chapters cover the introduction to biometrics, the detailed development of the WWOST-based feature extraction and matching framework, and a final conclusion confirming the performance superiority of the proposed approach.
Which keywords best describe this research?
Key terms include Biometrics, WWOST, Palmprint, Finger Knuckle-Print, Feature Fusion, and Phase-Only Correlation.
Why is WWOST considered an improvement over standard S-transform in this context?
WWOST enhances energy concentration in the signal and is more accurate for instantaneous frequency estimation, which significantly improves the discriminability of extracted palmprint features compared to standard S-transform methods.
How is the feature fusion performed in the proposed system?
The system fuses local features extracted via WWOST with global features extracted via Fourier transform coefficients using the Maximum Weighted rule, where weights are inversely proportional to the EER of each matcher.
- Quote paper
- N.B. Mahesh Kumar (Author), K. Premalatha (Author), 2016, Certain Investigations on Transform Based Techniques in Palmprint and Finger Knuckle-Print Biometrics for Personal Authentification, Munich, GRIN Verlag, https://www.grin.com/document/378795
