Tools
Tools
Backer, Rishan (2024) Combination of Face recognition and Handprint Biometrics with Fingerprint Image Encryption Using Multiple QR Decomposition. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (3MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (543kB) | Preview |
Abstract
In this project the different types of biometric traits are combined together by different methods and the encryption of fingerprint is also considered with the help of multiple QR decomposition method in order to enhance the security of the system. The major biometric traits are considered as palmprint biometric, fingerprint biometric and facial biometric. The different biometric traits are considered here because thus this can enhance the stability of biometric authentication. If we consider any single biometric trait for authentication, there is a high chance of failure of system in the future when the physical biometric trait of any person has any newly developed minor differences such as marks or cuts or nay physically damaged signs can also void the system’s authorization capability, thus in order to overcome this, the combination of biometrics are very important, this ensure the person was right even when the person was physically right person. But when considering any single biometric trait, the system will be wrong even though the person was physically right.
There are different biometric traits are available widely according to a human body, these biometric traits has its own advantages and disadvantages, here we are going to consider the biometric traits of the person such as palm print biometric, fingerprint biometric and face biometric trait. These biometrics are considered here because these can fit very well to my project, such as when considering the palm print biometric the unique characteristics of palm print are very different and has strong security unique features when compared to other biometric traits that are widely available, the area of features that is for palm print are larger when compared to other traits, this is the major reason for considering the palm biometric trait as an important trait here. Same character applied for fingerprint, the security features are high for fingerprint biometric when compared to any other biometric traits, the fingerprint biometrics are widely accepted. Finally, the face biometric has large biometric security features, which is considered as the strong biometric security authorization system here, because when the scanning technologies are capable enough to identify the person, the authorization will be strong and secure. This project excluded other biometric traits for example iris biometric, vein biometrics due to much more complex and time-consuming process and also the final efficiency will be very less as compared to the three biometric traits that we are considered here.
This project uses different types of tools and algorithms in order to achieve the result, the major tools and algorithm such as for adjusting contrast and equalization of captured biometric images, such as CLAHE, other tools such as for extracting the Region Of Interest. The function such as Softmax function is used for the calculation of similarities for each biometric trait are considered here. Finally, the algorithm such as Score Level fusion algorithm which is used to combine these identified biometric traits together in order to identify the person for authorization.
Through this tool the project aims to be successful project with more efficient way of authorization using these strong biometric traits with unique features, the achievability of these project is almost 100 % due to the unique biometric traits and these powerful algorithms and tools.
The project aims to capture different biometric traits without physically touching the scanner, that is one of the major advantages of this project because of contactless reading system can enhance the overall security and maintain the health of the human.
Thus, biometrics are initially gone for image acquisition process for capturing the biometrics and then the pre-processing are done for fine tuning and enhancing the quality of the image. Then, the next step is for the feature extraction process where the biometric unique features are extracted here. Finally, as the final step of authorization, these are then gone to similarity calculation and final evaluation process, where the authorization process is done and the identification of the real person with the help of these biometric traits are done here in this process. Finally, here we are doing the multiple QR decomposition method that is iterative matrix method in order to encrypt the fingerprint data to provide more security to the sensitive biometric data that are captured.
According to this, the final decision can be made by the authorization of the person’s different biometric traits and finding similarities and combining these biometric traits helps to identify the exact real person even though if there is any physical cuts or marks are present the system will not void its authorization and identification process, because the identification process is made by score level fusion method and thus a threshold score is set to identify the person as the result. It is found out that this method is more successful and secured method because it is also helps to encrypt the sensitive fingerprint data that are collected using multiple QR decomposition method.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email Monaghan, Mark UNSPECIFIED |
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Biometric Identification Q Science > QA Mathematics > Computer software > Computer Security T Technology > T Technology (General) > Information Technology > Computer software > Computer Security |
| Divisions: | School of Computing > Master of Science in Cyber Security |
| Depositing User: | Ciara O'Brien |
| Date Deposited: | 29 Jul 2025 10:26 |
| Last Modified: | 29 Jul 2025 10:26 |
| URI: | https://norma.ncirl.ie/id/eprint/8293 |
Actions (login required)
 |
View Item |