THE PALM PRINT RECOGNITION SYSTEM
ABSTRACT
Palmprint recognition has been investigated over ten year years. Palmprint is proven to be distinguishable from other features because of number of attributes. These attributes include color, clarity, position, continuity, length and variation in thickness. Lines are represented in a very efficient way and it needs low storage and consistency in detection and these are efficient for shape matching involving large database. But there will always be a problem of missing or broken lines during the extraction process of palmprint which causes difficulty in the matching process. Therefore, to eliminate this problem there is a need for efficient technique in order to reduce the number of repeated lines or broken lines in the binary images. This project proposed the use of 2-Dimensional Principal component analysis for palm print recognition. The proposed work was implemented using matlab (R2015a) software. Eigen vector was used to classify the data set obtained from 2D PCA and accuracy of 90% was obtained.
TABLE OF CONTENTS
Title page…………………………………………………………………………………………
Declaration……………………………………………………………………………………….
Certification……………………………………………………………………………………..
Dedication……………………………………………………………………………………….
Acknowledgement………………………………………………………………………………
Abstract………………………………………………………………………………………….
Table of content………………………………………………………………………………..
List of tables…………………………………………………………………………………..
List of figures……………………………………………………………………………………
CHAPTER ONE: INTRODUCTION…………………………………………………………
1.1 BACKGROUND OF STUDY……………………………………………………………….
1.2 PROBLEM STATEMENT………………………………………………………………….
1.3 SCOPE OF STUDY…………………………………………………………………………
1.4 AIMS AND OBJECTIVES…………………………………………………………………
1.5 SIGNIFICANCE OF STUDY………………………………………………………………
1.6 PROJECT LAYOUT………………………………………………………………………..
CHAPTER TWO: LITERATURE REVIEW……………………………………………….
2.1 PREABLE……………………………………………………………………………………
2.2 BIOMETRICS……………………………………………………………………………….
2.1.1CONCEPT OF PALMPRINT……………………………………………………
2.2.2PALM IDENTIFICATION……………………………………………………
2.3.3PALM RECOGNITION TECHNIQUE………………………………………
2.4.4HARDWARE……………………………………………………………………
2.5.5SOFTWARE……………………………………………………………………
CHAPTER THREE: RELATED WORK EXISTING SYSTEM…………………………….
3.1 ANALYSIS OF THE EXISTINGSYSTEM………………………………………………….
3.2 PROBLEM OF THE EXISTINGSYSTEM…………………………………………………..
3.3 PROPOSEDSYSTEM……………………………………………………………………
3.4 PROPOSED SYSTEM DESIGN…………………………………………………………
3.5 CHOICE OF PROGRAMMING TOOL…………………………………………………
CHAPTER FOUR: IMPLEMENTATION AND RESULT EVALUATION……………
4.1 DATA STRUCTURE…………………………………………………………………………
4.1.1 EXPERIMENT SETUP……………………………………………………………………
4.1.2 DATABASE SETTINGS………………………………………………………………….
4.2 USER INTERFACE………………………………………………………………………
4.3 INPUT DESIGN………………………………………………………………………………
4.4 OUTPUT DESIGN……………………………………………………………………………
4.5 CLASSIFICATION ACCURACY…………………………………………………………
CHAPTER FIVE: SUMMARY AND CONCLUSION ……………………………………
5.1 SUMMARY…………………………………………………………………………………
5.2 CONCLUSION………………………………………………………………………………
5.3 FUTURE WORK…………………………………………………………………………….
REFERENCES…………………………………………………………………………………..
APPENDIX…………………………………………………………………………………….
LIST OF FIGURE
3.1 proposed system design…………………………………………..
4.1Matlab work environment…………………………………………
4.2 User interface……………………………………………………..
4.3 Loading of the database……………………………………………
4.4 Pre-processing and normalization…………………………………
4.5 Database loaded and ready to be trained………………………….
4.6 Images trained using 2D-PCA…………………………………….
4.7 Palm print indicating recognition and time taken…………………
4.8 Image of a palm……………………………………………………
4.9 Image of another tested been recognized………………………….
4.10 Image of an unrecognized palm print……………………………
4.11 Image of a mismatched palm print………………………………
LIST OF TABLE
4.8 PCA classification Accuracy……………………………………….
LIST OF APPENDIX
CHAPTER ONE
INTRODUCTION
1.1 Background to the Study
Palm print recognition is one of the biometrics available at the present. Biometric systems are used two main categories ‘physiological’ and/or ‘behavioral’. The physiological category includes the physical human traits such as palm print, hand shape, eyes, veins, etc. The behavioral category includes the movement of the human, such as hand gesture, speaking style, signature (Jain, Bolle, & Pankanti 1999).
Palm prints are stable and show high accuracy in representing each individual’s identity. (Campbell, 2000) They have been commonly used in law enforcement and forensic environments. Since the surface of the palm print is larger than the fingerprint, a higher quantity of identifying features can be extracted from the palm print. Moreover, users consider hand biometrics as being user friendly, easy to use, and convenient. Palm print acquisition is based on standard charge-coupled device (CCD)-based optical scanning (Renold, 2010).
Palm print based biometric approaches have been intensively developed over a decade because they possess several advantages over other systems. Palm print images can be acquired with low resolution cameras and scanners and still have enough information to achieve good recognition rates. If high resolution images are captured, ridges and wrinkles can be detected (Jain, & Pankanti, 201). Forensic applications typically require high resolution imaging, with at least 500 dpi.
The palmprint is a relatively new biometric feature, has several advantages compared with currently available features (Maltoni, et al, 2004). The seven factors affect the determination of a biometric identifier in a particular application: universality, uniqueness, Permanence, collectability, performance, acceptability and circumvention. Palm print recognition has been introduced a decade ago. It has gradually attracted the attention of various researchers due to its richness in amount of features. Palm is the inner surface of the hand between the wrist and the fingers.
Palm print recognition has been introduced a decade ago. Palm is the inner surface of the hand between the wrist and the fingers. The Palm area contains a large number of features that can be used as biometric features such as Principal lines, geometry, wrinkle, delta point, minutiae, datum point features and texture. The principle lines are also called as flexion creases. The formation of these lines is related to the finger movements, tissue structures and the purpose of skin. Even the palm prints of identical twins are different (Biggun and Graland, 1987).
The measurement of these traits helps in authentication using the biometric systems. One of the most successful biometric systems is the palm print recognition system. This system recognizes on the basis of the palm print of a person. The interesting part is that the ridge structure is permanent. This ridge structure is formed at about the thirteenth week of the embryonic development. This formation gets completed by the eighteenth week. The palm print recognition system has advantages over the other physiological biometric systems. Some of the advantages are fixed line structure, low intrusiveness, low cost capturing device, low resolution imaging. Thus palmprint recognition is a very interesting research area. A lot of work has already been done in this area, but there is still a lot of scope to make the systems more efficient. Here, we have tried to analyze the already existing systems and thereby propose a new approach.
Palmprint recognition techniques have been grouped into two main categories, first approach is based on low-resolution features and second approach is based on high-resolution features. First approach make use of low-resolution images (such as 75 or 150 ppi), where only principal lines, wrinkles, and texture are extracted. Second approach uses high resolution images (such as 450 or 500 ppi), where in addition to principal lines and wrinkles, more discriminant features like ridges, singular points, and minutiae can be extracted (Brunelli & Poggio, 1993).
1.2 Problem Statement
There is a need for modern technology to use systems that recognize or verify the identity of people when performing task or transactions. Passwords or token suffer from loss or stolen problems. Thus, there is a need to develop more usable and secure system. The answer to this is using biometric systems.
The biometric systems that are used for commercial applications or forensic applications depend on many factors such as, real-time processing, high accuracy, low complexity, low cost and design simplicity. The palmprint recognition systems which are used for commercial applications require features such as principal lines and wrinkles which extracted from low resolution images. Workers and old people may not provide clear physiological features such as fingerprints or voice because of their problematic skin caused by physical work. Recently, voice, face, and iris-based verifications have been studied extensively. The development of multiscale image transforms provides the biometric systems with transformations which deal with low resolution images to identify the individuals from their palmprints. The combination between multiscale image transform together with 2D projection technique and back-propagation neural network will be used in this research.
1.3 Scope of the Study
This research work is dedicated to bridging the gap on the recognition system based on palmprint features. This project will only cover the area of using the Palm print can be captured by widely used CCD based palm print scanners, video cameras, Digital cameras and Digital Scanner. a CCD based palm print scanner attracts the most of the researchers for acquiring the image because the scanner have pegs for guiding the placement of hands. After the analysis of the existing system, some areas were noted for improvement.
1.4 Aim and Objectives
The proposed system is aimed at the development of a palmprint verification system in the examination arena of Alhikmah University Ilorin, Kwara State. This aim will be achieved through the following objectives:
i. To build a recognition system based on palmprint features.
ii. To apply multiscale transform for palmprint images in order to extract features.
iii. To apply dimensionality reduction technique to extract fine features and reduce features size.
iv. To model the recognition of the extracted features by using feed-forward back-propagation neural network.
1.5 Significance of the Study
Palm print recognition has been investigated over past several years. Palm print based personal verification has quickly entered the biometric family due to its ease of acquisition, high user acceptance and reliability. Here we have presented brief review in palm print identification system. Biometric palm print recognizes a person based on the principal lines, wrinkles and ridges on the surface of the palm. These line structures are stable and remain unchanged throughout the life of an individual. More importantly, no two palm prints from differentindividuals are the same, and normally people do not feel uneasy to have their palm print images taken for testing. It offers promising future for medium-security access control system.
CHAPTER TWO
LITERATURE REVIEW
2.0 Preamble
In this section of literature review, the following topics are discussed:
Biometrics, Biometric limitations, secured biometrics, biometric performance analysis, accurate biometric system, multiple modalities, multimodal biometrics, fusion levels, fusion strategies, fusion scenario, Palm as a biometric, palm feature, palm feature extractions methods, edge detection methods, feature level fusion, feature compatibility and approaches.
2.1 Biometrics
Biometrics is a Greek term defining bios as life and metric as a measurement. Biometrics is basically a pattern recognition system using human characters recognition. History says that astrologers studied palm prints in predicting the future. Finger prints were used in olden days as a mark of authentication of a document. Behavioral characters like signature are used from olden days to identify a person. With the growing technology and rapid growth in applications of various fields like communication, networking, banking, and highly secure applications like criminal detection, forensic, military security, we can see tremendous growth in the field of biometrics to fulfill the demands of get reliable, cost effective, user friendly system.
Anil K Jain, (2014) introduces the biometric recognition which works in verification mode or identification mode. Identity of a person is established by comparing the input data with the stored template data. Author gives the basic biometric system operation modes as sensor level which captures the input data, feature level which extracts the features of collected data, match score level which estimates the degree of matching between input data and stored data, and a decision level which decides to either accept or reject the input. Author presents an overview of errors that could occur in the biometrics as false match and false mismatch. Biometric limitations like noisy sensor data, inter and intra user variations, spoof attacks, etc., are presented Kong & Ross (2011) presented biometrics as a promising frontier for the identification. He describes biometric can be knowledge based like pass words or token based like ID cards. A comparison of face, finger print, hand and iris based on universality, acceptability, permanence, uniqueness is presented as a case study and summarized that biometrics will likely be used in almost every transaction. Even years after the author’s observation, biometrics has found its place in every transaction of a modern world.
Publications related to biometrics are found in the literature from 1998 onwards and later within a decade a tremendous growth in research publications are seen. James Wayman (2007) describes taxonomy of uses, various issues like performance of a biometric system. This paper gives applications, taxonomy of uses, habituated vs non-habituated, public vs private, open vs closed, classification of applications, system model of biometric system.
You et al (2009) in his patent presented an integrated multisensory recognition system using acoustic and visual features for person identification. Integration of multiple information was a key issue in implementation of a reliable system. The work was carried out using acoustic and visual features of a person for identification. The speaker and face recognition systems are decomposed into two and three single feature classifier respectively. The resulting five classifiers produce non homogenous scores which are combined using different approaches. The speaker recognition is based on vector quantization of the acoustic parameter space.
2.1.1 Concept of Palm Print
.