Contactless palmprint verification using siamese networks
In our modern world, biometric based identification has become a widely adopted standard to verify the identity of a person. Biometric based identification technology can be seen taking multiple forms. From the straightforward thumbprint authentication mechanism in mobile phones up until the intrica...
Saved in:
Main Author: | |
---|---|
Format: | Final Year Project / Dissertation / Thesis |
Published: |
2022
|
Subjects: | |
Online Access: | http://eprints.utar.edu.my/4661/1/fyp_CS_2022_NJH.pdf http://eprints.utar.edu.my/4661/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my-utar-eprints.4661 |
---|---|
record_format |
eprints |
spelling |
my-utar-eprints.46612023-01-15T13:28:04Z Contactless palmprint verification using siamese networks Ng, Jan Hui Q Science (General) T Technology (General) In our modern world, biometric based identification has become a widely adopted standard to verify the identity of a person. Biometric based identification technology can be seen taking multiple forms. From the straightforward thumbprint authentication mechanism in mobile phones up until the intricate industrial grade biometrics fusion technology. Due to the COVID-19 pandemic, biometric based authentication systems have become increasingly in demand due to its ease of configuration and convenience of usage. Additionally, the contactless input retrieval nature of biometric based authentication systems plays a big part in greatly reducing the risks of the virus transmission. In view of the current situation, this project aims to implement a contactless palmprint recognition system as a means to authenticate users in a more hygienic way. This contactless palmprint recognition system aims to also bring a fresh perspective to the overly saturated scene of biometric authentication that are typically based on facial features, fingerprint features and other mainstream biometric features. The outcome of the project is to deliver a system that can perform contactless palmprint recognition in four main stages via computer vision techniques and Siamese neural networks. The four main stages are – Palmprint Image Input, Region of interest segmentation, Feature extraction and Verification. The novelties of this project are the algorithm used to segment the feature abundant region of interest from the palm image, and also the usage of a custom-built Siamese Network utilising a state-of-the-art CNN called EfficientNet as the underlying feature extractor. All in all, this project intends to act as an alternative check in system for users that can be used in a wide variety of scenarios such as digital contact tracing, attendance tracking, registration purposes and more. 2022-04-21 Final Year Project / Dissertation / Thesis NonPeerReviewed application/pdf http://eprints.utar.edu.my/4661/1/fyp_CS_2022_NJH.pdf Ng, Jan Hui (2022) Contactless palmprint verification using siamese networks. Final Year Project, UTAR. http://eprints.utar.edu.my/4661/ |
institution |
Universiti Tunku Abdul Rahman |
building |
UTAR Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Tunku Abdul Rahman |
content_source |
UTAR Institutional Repository |
url_provider |
http://eprints.utar.edu.my |
topic |
Q Science (General) T Technology (General) |
spellingShingle |
Q Science (General) T Technology (General) Ng, Jan Hui Contactless palmprint verification using siamese networks |
description |
In our modern world, biometric based identification has become a widely adopted standard to verify the identity of a person. Biometric based identification technology can be seen taking multiple forms. From the straightforward thumbprint authentication mechanism in mobile phones up until the intricate industrial grade biometrics fusion technology.
Due to the COVID-19 pandemic, biometric based authentication systems have become increasingly in demand due to its ease of configuration and convenience of usage. Additionally, the contactless input retrieval nature of biometric based authentication systems plays a big part in greatly reducing the risks of the virus transmission. In view of the current situation, this project aims to implement a contactless palmprint recognition system as a means to authenticate users in a more hygienic way. This contactless palmprint recognition system aims to also bring a fresh perspective to the overly saturated scene of biometric authentication that are typically based on facial features, fingerprint features and other mainstream biometric features.
The outcome of the project is to deliver a system that can perform contactless palmprint recognition in four main stages via computer vision techniques and Siamese neural networks. The four main stages are – Palmprint Image Input, Region of interest segmentation, Feature extraction and Verification.
The novelties of this project are the algorithm used to segment the feature abundant region of interest from the palm image, and also the usage of a custom-built Siamese Network utilising a state-of-the-art CNN called EfficientNet as the underlying feature extractor.
All in all, this project intends to act as an alternative check in system for users that can be used in a wide variety of scenarios such as digital contact tracing, attendance tracking, registration purposes and more. |
format |
Final Year Project / Dissertation / Thesis |
author |
Ng, Jan Hui |
author_facet |
Ng, Jan Hui |
author_sort |
Ng, Jan Hui |
title |
Contactless palmprint verification using siamese networks
|
title_short |
Contactless palmprint verification using siamese networks
|
title_full |
Contactless palmprint verification using siamese networks
|
title_fullStr |
Contactless palmprint verification using siamese networks
|
title_full_unstemmed |
Contactless palmprint verification using siamese networks
|
title_sort |
contactless palmprint verification using siamese networks |
publishDate |
2022 |
url |
http://eprints.utar.edu.my/4661/1/fyp_CS_2022_NJH.pdf http://eprints.utar.edu.my/4661/ |
_version_ |
1755876965301092352 |
score |
13.160551 |