Face Age Classification based on Moment Features
碩士 === 國立暨南國際大學 === 電機工程學系 === 99 === In recent years the community increased emphasis on security issues, the biometric identification technology began to be accepted by the public. In this thesis, we discuss the face age classification system based on moment features. The framework of our proposed...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2011
|
Online Access: | http://ndltd.ncl.edu.tw/handle/79920278613703826943 |
id |
ndltd-TW-099NCNU0442121 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-099NCNU04421212015-10-23T06:50:20Z http://ndltd.ncl.edu.tw/handle/79920278613703826943 Face Age Classification based on Moment Features 基於矩特徵之人臉年齡分類 Chen, Jen-Yuan 陳振淵 碩士 國立暨南國際大學 電機工程學系 99 In recent years the community increased emphasis on security issues, the biometric identification technology began to be accepted by the public. In this thesis, we discuss the face age classification system based on moment features. The framework of our proposed age classification system includes three modules, which are the pre-processing module, feature extraction and classification module. Firstly, the image extracted the region of interesting by the detector, then moment features will transform images into the feature vector, and finally to the identification classifier. In this thesis, we experiment several moment features, such as Hu Moment Invariant, Geometric Moment and Zernike Moment on age classification. In this thesis, we use FG-NET aging database, a total of 1002 color or gray-scale face images. According to the experimental results, using Geometric Moment with SVM is the best. We obtained 84.6% in the FG-NET aging database. Chen, Wen-Shiung 陳文雄 2011 學位論文 ; thesis 38 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立暨南國際大學 === 電機工程學系 === 99 === In recent years the community increased emphasis on security issues, the biometric identification technology began to be accepted by the public. In this thesis, we discuss the face age classification system based on moment features.
The framework of our proposed age classification system includes three modules, which are the pre-processing module, feature extraction and classification module. Firstly, the image extracted the region of interesting by the detector, then moment features will transform images into the feature vector, and finally to the identification classifier. In this thesis, we experiment several moment features, such as Hu Moment Invariant, Geometric Moment and Zernike Moment on age classification.
In this thesis, we use FG-NET aging database, a total of 1002 color or gray-scale face images. According to the experimental results, using Geometric Moment with SVM is the best. We obtained 84.6% in the FG-NET aging database.
|
author2 |
Chen, Wen-Shiung |
author_facet |
Chen, Wen-Shiung Chen, Jen-Yuan 陳振淵 |
author |
Chen, Jen-Yuan 陳振淵 |
spellingShingle |
Chen, Jen-Yuan 陳振淵 Face Age Classification based on Moment Features |
author_sort |
Chen, Jen-Yuan |
title |
Face Age Classification based on Moment Features |
title_short |
Face Age Classification based on Moment Features |
title_full |
Face Age Classification based on Moment Features |
title_fullStr |
Face Age Classification based on Moment Features |
title_full_unstemmed |
Face Age Classification based on Moment Features |
title_sort |
face age classification based on moment features |
publishDate |
2011 |
url |
http://ndltd.ncl.edu.tw/handle/79920278613703826943 |
work_keys_str_mv |
AT chenjenyuan faceageclassificationbasedonmomentfeatures AT chénzhènyuān faceageclassificationbasedonmomentfeatures AT chenjenyuan jīyújǔtèzhēngzhīrénliǎnniánlíngfēnlèi AT chénzhènyuān jīyújǔtèzhēngzhīrénliǎnniánlíngfēnlèi |
_version_ |
1718110158690713600 |