Contactless palm print recognition: Novel design and palm openness classification
(2023) In Master's Theses in Mathematical Sciences FMAM05 20231Mathematics (Faculty of Engineering)
- Abstract (Swedish)
- Biometric technologies, such as facial and fingerprint recognition, have become widely adopted for identity verification in various applications. Palm biometrics, utilizing the unique patterns of the human palm, has gained significant attention for its accuracy and security. This thesis aims to investigate and propose a comprehensive design for certain as- pects of a contactless palm print recognition system, taking into account the issue of usability and palm openness. Contactless palm print recog- nition offers several advantages over other commonly adopted biometric systems. Firstly, it can operate effectively with low-resolution images and inexpensive cameras, making it more cost-efficient. However, the most significant advantage,... (More)
- Biometric technologies, such as facial and fingerprint recognition, have become widely adopted for identity verification in various applications. Palm biometrics, utilizing the unique patterns of the human palm, has gained significant attention for its accuracy and security. This thesis aims to investigate and propose a comprehensive design for certain as- pects of a contactless palm print recognition system, taking into account the issue of usability and palm openness. Contactless palm print recog- nition offers several advantages over other commonly adopted biometric systems. Firstly, it can operate effectively with low-resolution images and inexpensive cameras, making it more cost-efficient. However, the most significant advantage, particularly in the present circumstances, is its hygienic nature. But the technology also comes with new challenges: distance to the camera and the changes in palm print due to palm open- ness to name a few. Through the employment of transfer learning and landmark-based methods, the classification of palm openness from in- put images achieved an average accuracy of 0.90. In conclusion, despite their perceived visual quality, openness creates slight variations in width, depth, and crease distances on the palm print, which in turn affects the matching between images. Our results indicate that palm images are best matched to ones of the same openness. These findings validate the importance of palm openness and its impact on system performance, as well as the ability of the classifier to correctly classify the openness. By addressing these challenges, we can improve the accuracy and applicab- ility of contactless palm print recognition technology. (Less)
- Popular Abstract
- Improving Contactless Palm Print Recognition Technology
Biometric technologies, such as facial and fingerprint recognition, have become widely used for identity verification in various applications. An- other promising biometric solution is palm biometrics, which utilizes the unique patterns found on the human palm for accurate and secure iden- tification. This thesis focuses on investigating and proposing a compre- hensive design for a contactless palm print recognition system.
Contactless palm print recognition offers advantages such as cost-efficiency and hygiene. However, challenges arise from factors like camera distance and variations in palm openness. By utilizing machine learning and im- age analysis techniques, the thesis... (More) - Improving Contactless Palm Print Recognition Technology
Biometric technologies, such as facial and fingerprint recognition, have become widely used for identity verification in various applications. An- other promising biometric solution is palm biometrics, which utilizes the unique patterns found on the human palm for accurate and secure iden- tification. This thesis focuses on investigating and proposing a compre- hensive design for a contactless palm print recognition system.
Contactless palm print recognition offers advantages such as cost-efficiency and hygiene. However, challenges arise from factors like camera distance and variations in palm openness. By utilizing machine learning and im- age analysis techniques, the thesis achieves an average accuracy of 0.90 in classifying palm openness from input images. This means that the system can effectively determine whether a palm is more closed or open based on the captured image. The research also reveals that variations in palm openness lead to slight differences in the width, depth, and crease distances of the palm print, affecting the matching process between im- ages. The findings demonstrate that palm images are best matched with others of the same level of openness.
These results highlight the significance of considering palm openness and its impact on the performance of contactless palm print recognition sys- tems. Additionally, the study validates the classifier’s ability to correctly classify palm openness. By addressing these challenges and taking palm openness into account, the accuracy and applicability of contactless palm print recognition technology can be improved.
Enhancing contactless palm print recognition technology is crucial for its widespread adoption in various identity verification applications. The improvements in accuracy and reliability achieved through this research can lead to more secure and efficient systems, while also ensuring a hy- gienic and convenient user experience. (Less)
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/student-papers/record/9126492
- author
- Mahdavi Khayavi, Simon LU and Li, Leo Yi-Lei LU
- supervisor
-
- Anders Heyden LU
- Filip Winzell LU
- organization
- course
- FMAM05 20231
- year
- 2023
- type
- H2 - Master's Degree (Two Years)
- subject
- publication/series
- Master's Theses in Mathematical Sciences
- report number
- LUTFMA-3516-2023
- ISSN
- 1404-6342
- other publication id
- 2023:E49
- language
- English
- id
- 9126492
- date added to LUP
- 2023-08-22 17:12:20
- date last changed
- 2023-08-22 17:12:20
@misc{9126492,
abstract = {{Biometric technologies, such as facial and fingerprint recognition, have become widely adopted for identity verification in various applications. Palm biometrics, utilizing the unique patterns of the human palm, has gained significant attention for its accuracy and security. This thesis aims to investigate and propose a comprehensive design for certain as- pects of a contactless palm print recognition system, taking into account the issue of usability and palm openness. Contactless palm print recog- nition offers several advantages over other commonly adopted biometric systems. Firstly, it can operate effectively with low-resolution images and inexpensive cameras, making it more cost-efficient. However, the most significant advantage, particularly in the present circumstances, is its hygienic nature. But the technology also comes with new challenges: distance to the camera and the changes in palm print due to palm open- ness to name a few. Through the employment of transfer learning and landmark-based methods, the classification of palm openness from in- put images achieved an average accuracy of 0.90. In conclusion, despite their perceived visual quality, openness creates slight variations in width, depth, and crease distances on the palm print, which in turn affects the matching between images. Our results indicate that palm images are best matched to ones of the same openness. These findings validate the importance of palm openness and its impact on system performance, as well as the ability of the classifier to correctly classify the openness. By addressing these challenges, we can improve the accuracy and applicab- ility of contactless palm print recognition technology.}},
author = {{Mahdavi Khayavi, Simon and Li, Leo Yi-Lei}},
issn = {{1404-6342}},
language = {{eng}},
note = {{Student Paper}},
series = {{Master's Theses in Mathematical Sciences}},
title = {{Contactless palm print recognition: Novel design and palm openness classification}},
year = {{2023}},
}