Age and Gender Recognition with Random Occluded Data Augmentation on Facial Images
碩士 === 國立臺灣科技大學 === 電子工程系 === 107 === Facial analysis tasks have always been hot topics over the years for their broad varieties of applications, such as surveillance, commercial uses, human-machine interaction, and entertainment, etc. With the recent success of deep learning, these facial analysis...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
2019
|
Online Access: | http://ndltd.ncl.edu.tw/handle/275fd8 |
id |
ndltd-TW-107NTUS5427096 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-107NTUS54270962019-10-23T05:46:05Z http://ndltd.ncl.edu.tw/handle/275fd8 Age and Gender Recognition with Random Occluded Data Augmentation on Facial Images 基於隨機影像遮蔽式資料擴增之臉部年齡及性別辨識 Chia-Yuan Hsu 許家源 碩士 國立臺灣科技大學 電子工程系 107 Facial analysis tasks have always been hot topics over the years for their broad varieties of applications, such as surveillance, commercial uses, human-machine interaction, and entertainment, etc. With the recent success of deep learning, these facial analysis tasks were able to tackle more the difficult and practical situations. However, while some tasks like age and gender estimation did achieve substantial improvements to the traditional machine learning based methods, they are still far from perfect to satisfy the need of real-life applications. This thesis proposed a data augmentation method by altering the training images that resemble real-life photos to improve the performance of the networks by providing more varieties to the training samples. The proposed method, Random Occlusion, adopted three simple occlusion techniques, Blackout, Random Brightness, and Blur, each simulating a different kind of challenge that would be encountered in real-world applications. We verify the effectiveness of our proposed method by implementing the augmentation method on two convolution neural networks (CNNs), the modified AdienceNet and VGG16 to perform age and gender classification. The proposed augmentation method improves the age accuracy results of the modified the AdienceNet and VGG16 by 1.0% and 0.8%, respectively; and gender accuracy results of the AdienceNet and VGG16 by 1.5% and 1.2%, respectively. Chang-Hong Lin 林昌鴻 2019 學位論文 ; thesis 49 en_US |
collection |
NDLTD |
language |
en_US |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立臺灣科技大學 === 電子工程系 === 107 === Facial analysis tasks have always been hot topics over the years for their broad varieties of applications, such as surveillance, commercial uses, human-machine interaction, and entertainment, etc. With the recent success of deep learning, these facial analysis tasks were able to tackle more the difficult and practical situations. However, while some tasks like age and gender estimation did achieve substantial improvements to the traditional machine learning based methods, they are still far from perfect to satisfy the need of real-life applications. This thesis proposed a data augmentation method by altering the training images that resemble real-life photos to improve the performance of the networks by providing more varieties to the training samples. The proposed method, Random Occlusion, adopted three simple occlusion techniques, Blackout, Random Brightness, and Blur, each simulating a different kind of challenge that would be encountered in real-world applications. We verify the effectiveness of our proposed method by implementing the augmentation method on two convolution neural networks (CNNs), the modified AdienceNet and VGG16 to perform age and gender classification. The proposed augmentation method improves the age accuracy results of the modified the AdienceNet and VGG16 by 1.0% and 0.8%, respectively; and gender accuracy results of the AdienceNet and VGG16 by 1.5% and 1.2%, respectively.
|
author2 |
Chang-Hong Lin |
author_facet |
Chang-Hong Lin Chia-Yuan Hsu 許家源 |
author |
Chia-Yuan Hsu 許家源 |
spellingShingle |
Chia-Yuan Hsu 許家源 Age and Gender Recognition with Random Occluded Data Augmentation on Facial Images |
author_sort |
Chia-Yuan Hsu |
title |
Age and Gender Recognition with Random Occluded Data Augmentation on Facial Images |
title_short |
Age and Gender Recognition with Random Occluded Data Augmentation on Facial Images |
title_full |
Age and Gender Recognition with Random Occluded Data Augmentation on Facial Images |
title_fullStr |
Age and Gender Recognition with Random Occluded Data Augmentation on Facial Images |
title_full_unstemmed |
Age and Gender Recognition with Random Occluded Data Augmentation on Facial Images |
title_sort |
age and gender recognition with random occluded data augmentation on facial images |
publishDate |
2019 |
url |
http://ndltd.ncl.edu.tw/handle/275fd8 |
work_keys_str_mv |
AT chiayuanhsu ageandgenderrecognitionwithrandomoccludeddataaugmentationonfacialimages AT xǔjiāyuán ageandgenderrecognitionwithrandomoccludeddataaugmentationonfacialimages AT chiayuanhsu jīyúsuíjīyǐngxiàngzhēbìshìzīliàokuòzēngzhīliǎnbùniánlíngjíxìngbiébiànshí AT xǔjiāyuán jīyúsuíjīyǐngxiàngzhēbìshìzīliàokuòzēngzhīliǎnbùniánlíngjíxìngbiébiànshí |
_version_ |
1719276324883791872 |