Utilizing Motion Data Retrieval Techniques for Person Identification

碩士 === 國立成功大學 === 工程科學系 === 104 === Identifying a specific user is an old but challenging problem, and its applications are ubiquitous in our daily lives. For example, we have to prove our identity to gain access to a bank account when using the cash machine. Conventional person identification metho...

Full description

Bibliographic Details
Main Authors: Jing-FuJuang, 莊景富
Other Authors: Wei-Guang Teng
Format: Others
Language:en_US
Published: 2016
Online Access:http://ndltd.ncl.edu.tw/handle/42680055001258767787
id ndltd-TW-104NCKU5028111
record_format oai_dc
spelling ndltd-TW-104NCKU50281112017-09-24T04:40:46Z http://ndltd.ncl.edu.tw/handle/42680055001258767787 Utilizing Motion Data Retrieval Techniques for Person Identification 以體感資料檢索技術實現身分辨識 Jing-FuJuang 莊景富 碩士 國立成功大學 工程科學系 104 Identifying a specific user is an old but challenging problem, and its applications are ubiquitous in our daily lives. For example, we have to prove our identity to gain access to a bank account when using the cash machine. Conventional person identification methods are using an ID card or the combination of a username and password. Recently, new techniques based on biometrics have been introduced so that people do not need to worry if they forget their username and password. For example, fingerprint and iris recognition are becoming common methods of person identification; however, users are usually required to interact with a system to use these traits. In some non-critical situations, it may be more convenient to utilize soft biometrics for person identification, although these features are not as unique for a specific person. In this work, we propose to conduct gait analysis that can be performed from a distance without disturbing user activities. We utilize depth cameras to capture user movements and create motion sequences. Then, a motion sequence is transformed to a motion string with appropriate data preprocessing and clustering techniques. Representative motion strings representing the individual behaviour of a user are retrieved and utilized to identify people. Empirical studies based on real motion data show that our approach performs well in person identification. Wei-Guang Teng 鄧維光 2016 學位論文 ; thesis 45 en_US
collection NDLTD
language en_US
format Others
sources NDLTD
description 碩士 === 國立成功大學 === 工程科學系 === 104 === Identifying a specific user is an old but challenging problem, and its applications are ubiquitous in our daily lives. For example, we have to prove our identity to gain access to a bank account when using the cash machine. Conventional person identification methods are using an ID card or the combination of a username and password. Recently, new techniques based on biometrics have been introduced so that people do not need to worry if they forget their username and password. For example, fingerprint and iris recognition are becoming common methods of person identification; however, users are usually required to interact with a system to use these traits. In some non-critical situations, it may be more convenient to utilize soft biometrics for person identification, although these features are not as unique for a specific person. In this work, we propose to conduct gait analysis that can be performed from a distance without disturbing user activities. We utilize depth cameras to capture user movements and create motion sequences. Then, a motion sequence is transformed to a motion string with appropriate data preprocessing and clustering techniques. Representative motion strings representing the individual behaviour of a user are retrieved and utilized to identify people. Empirical studies based on real motion data show that our approach performs well in person identification.
author2 Wei-Guang Teng
author_facet Wei-Guang Teng
Jing-FuJuang
莊景富
author Jing-FuJuang
莊景富
spellingShingle Jing-FuJuang
莊景富
Utilizing Motion Data Retrieval Techniques for Person Identification
author_sort Jing-FuJuang
title Utilizing Motion Data Retrieval Techniques for Person Identification
title_short Utilizing Motion Data Retrieval Techniques for Person Identification
title_full Utilizing Motion Data Retrieval Techniques for Person Identification
title_fullStr Utilizing Motion Data Retrieval Techniques for Person Identification
title_full_unstemmed Utilizing Motion Data Retrieval Techniques for Person Identification
title_sort utilizing motion data retrieval techniques for person identification
publishDate 2016
url http://ndltd.ncl.edu.tw/handle/42680055001258767787
work_keys_str_mv AT jingfujuang utilizingmotiondataretrievaltechniquesforpersonidentification
AT zhuāngjǐngfù utilizingmotiondataretrievaltechniquesforpersonidentification
AT jingfujuang yǐtǐgǎnzīliàojiǎnsuǒjìshùshíxiànshēnfēnbiànshí
AT zhuāngjǐngfù yǐtǐgǎnzīliàojiǎnsuǒjìshùshíxiànshēnfēnbiànshí
_version_ 1718540076045041664