A Machine Learning Based Secure Face Verification Scheme and Its Applications to Digital Surveillance
碩士 === 國立臺灣大學 === 資訊工程學研究所 === 106 === Face Verification is a well known image analysis application and wildly used for recognizing individuals in contemporary society. However, in real applications, some of recognition systems ignore the importance of protecting the facial images that are used for...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
2017
|
Online Access: | http://ndltd.ncl.edu.tw/handle/h75bme |
id |
ndltd-TW-106NTU05392015 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-106NTU053920152019-05-16T00:22:54Z http://ndltd.ncl.edu.tw/handle/h75bme A Machine Learning Based Secure Face Verification Scheme and Its Applications to Digital Surveillance 以機器學習為基礎的加密臉部辨識方法及其在數位監控上之應用 Huan-Chih Wang 王煥智 碩士 國立臺灣大學 資訊工程學研究所 106 Face Verification is a well known image analysis application and wildly used for recognizing individuals in contemporary society. However, in real applications, some of recognition systems ignore the importance of protecting the facial images that are used for verification. If the facial images are not protected, malicious people can steal and copy the images to disguise as someone else. To conquer this problem, we design a secure face verification system that can also protect the facial images to be imitated. In our work, we use the DeepID2 convolutional neural network to extract the feature of a facial image and use the EM algorithm to do the facial verification problem. In order to keep the facial images privacy, we use the homomorphic encryption scheme to encrypt the facial data and compute the EM algorithm in the ciphertext domain. Based on difference privacy concerns, we build up three face recognition systems for surveillance or entry and exist control of a local community. Lastly, we conduct experiments of accuracy and time consuming and compare pros can cons between these systems. 吳家麟 2017 學位論文 ; thesis 42 en_US |
collection |
NDLTD |
language |
en_US |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立臺灣大學 === 資訊工程學研究所 === 106 === Face Verification is a well known image analysis application and wildly used for recognizing individuals in contemporary society. However, in real applications, some of recognition systems ignore the importance of protecting the facial images that are used for verification. If the facial images are not protected, malicious people can steal and copy the images to disguise as someone else. To conquer this problem, we design a secure face verification system that can also protect the facial images to be imitated. In our work, we use the DeepID2 convolutional neural network to extract the feature of a facial image and use the EM algorithm to do the facial verification problem. In order to keep the facial images privacy, we use the homomorphic encryption scheme to encrypt the facial data and compute the EM algorithm in the ciphertext domain. Based on difference privacy concerns, we build up three face recognition systems for surveillance or entry and exist control of a local community. Lastly, we conduct experiments of accuracy and time consuming and compare pros can cons between these systems.
|
author2 |
吳家麟 |
author_facet |
吳家麟 Huan-Chih Wang 王煥智 |
author |
Huan-Chih Wang 王煥智 |
spellingShingle |
Huan-Chih Wang 王煥智 A Machine Learning Based Secure Face Verification Scheme and Its Applications to Digital Surveillance |
author_sort |
Huan-Chih Wang |
title |
A Machine Learning Based Secure Face Verification Scheme and Its Applications to Digital Surveillance |
title_short |
A Machine Learning Based Secure Face Verification Scheme and Its Applications to Digital Surveillance |
title_full |
A Machine Learning Based Secure Face Verification Scheme and Its Applications to Digital Surveillance |
title_fullStr |
A Machine Learning Based Secure Face Verification Scheme and Its Applications to Digital Surveillance |
title_full_unstemmed |
A Machine Learning Based Secure Face Verification Scheme and Its Applications to Digital Surveillance |
title_sort |
machine learning based secure face verification scheme and its applications to digital surveillance |
publishDate |
2017 |
url |
http://ndltd.ncl.edu.tw/handle/h75bme |
work_keys_str_mv |
AT huanchihwang amachinelearningbasedsecurefaceverificationschemeanditsapplicationstodigitalsurveillance AT wánghuànzhì amachinelearningbasedsecurefaceverificationschemeanditsapplicationstodigitalsurveillance AT huanchihwang yǐjīqìxuéxíwèijīchǔdejiāmìliǎnbùbiànshífāngfǎjíqízàishùwèijiānkòngshàngzhīyīngyòng AT wánghuànzhì yǐjīqìxuéxíwèijīchǔdejiāmìliǎnbùbiànshífāngfǎjíqízàishùwèijiānkòngshàngzhīyīngyòng AT huanchihwang machinelearningbasedsecurefaceverificationschemeanditsapplicationstodigitalsurveillance AT wánghuànzhì machinelearningbasedsecurefaceverificationschemeanditsapplicationstodigitalsurveillance |
_version_ |
1719165175494344704 |