Age Estimation on Human Face Image Using Support Vector Regression and Texture-Based Features
This paper proposed a framework for estimating human age using facial features. These features exploit facial region information, such as wrinkles on the eye and cheek, which are then represented as a texture-based feature. Our proposed framework has several steps: preprocessing, feature extraction...
Saved in:
Main Authors: | , |
---|---|
Format: | Article PeerReviewed |
Language: | English |
Published: |
The Science and Information (SAI)
2022
|
Subjects: | |
Online Access: | https://repository.ugm.ac.id/279161/1/Amelia_PA.pdf https://repository.ugm.ac.id/279161/ https://www.ijacsa.thesai.org |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Universitas Gadjah Mada |
Language: | English |
id |
id-ugm-repo.279161 |
---|---|
record_format |
dspace |
spelling |
id-ugm-repo.2791612023-11-03T02:07:22Z https://repository.ugm.ac.id/279161/ Age Estimation on Human Face Image Using Support Vector Regression and Texture-Based Features Amelia, Jesy S Wahyono, Wahyono Information and Computing Sciences This paper proposed a framework for estimating human age using facial features. These features exploit facial region information, such as wrinkles on the eye and cheek, which are then represented as a texture-based feature. Our proposed framework has several steps: preprocessing, feature extraction, and age estimation. In this research, three feature extraction methods and their combination are performed, such as Local Binary Pattern (LBP), Local Phrase Quantization (LPQ), and Binarized Statistical Image Feature (BSIF). After extracting the feature, Principle Component Analysis (PCA) was performed to reduce the feature size. Finally, the Support Vector Regression (SVR) method was used to predict age. In evaluation, the estimation error will be based on mean average error (MAE). In the experiment, we utilized the well-known public dataset, face-age.zip, and UTK Face datasets, containing 15,202 facial image data. The data were divided into the training of 12,162 images and the testing of 3,040 images. Our experiments found that combining BSIF and LPQ with PCA achieved the lowest MAE of 9.766 and 9.754. The results show that the texture-based feature could be utilized for estimating the age on facial image. The Science and Information (SAI) 2022 Article PeerReviewed application/pdf en https://repository.ugm.ac.id/279161/1/Amelia_PA.pdf Amelia, Jesy S and Wahyono, Wahyono (2022) Age Estimation on Human Face Image Using Support Vector Regression and Texture-Based Features. (IJACSA) International Journal of Advanced Computer Science and Applications, 13 (2). pp. 122-129. ISSN 2156-5570 https://www.ijacsa.thesai.org |
institution |
Universitas Gadjah Mada |
building |
UGM Library |
continent |
Asia |
country |
Indonesia Indonesia |
content_provider |
UGM Library |
collection |
Repository Civitas UGM |
language |
English |
topic |
Information and Computing Sciences |
spellingShingle |
Information and Computing Sciences Amelia, Jesy S Wahyono, Wahyono Age Estimation on Human Face Image Using Support Vector Regression and Texture-Based Features |
description |
This paper proposed a framework for estimating human age using facial features. These features exploit facial
region information, such as wrinkles on the eye and cheek, which are then represented as a texture-based feature. Our proposed framework has several steps: preprocessing, feature extraction, and age estimation. In this research, three feature extraction methods and their combination are performed, such as Local Binary Pattern (LBP), Local Phrase Quantization (LPQ), and Binarized Statistical Image Feature (BSIF). After extracting the feature, Principle Component Analysis (PCA) was performed to reduce the feature size. Finally, the Support Vector Regression (SVR) method was used to predict age. In evaluation, the estimation error will be based on mean average error (MAE). In the experiment, we utilized the well-known public dataset, face-age.zip, and UTK Face datasets, containing 15,202 facial image data. The data were divided into the training of 12,162 images and the testing of 3,040 images. Our experiments found that
combining BSIF and LPQ with PCA achieved the lowest MAE of
9.766 and 9.754. The results show that the texture-based feature could be utilized for estimating the age on facial image. |
format |
Article PeerReviewed |
author |
Amelia, Jesy S Wahyono, Wahyono |
author_facet |
Amelia, Jesy S Wahyono, Wahyono |
author_sort |
Amelia, Jesy S |
title |
Age Estimation on Human Face Image Using Support Vector Regression and Texture-Based Features |
title_short |
Age Estimation on Human Face Image Using Support Vector Regression and Texture-Based Features |
title_full |
Age Estimation on Human Face Image Using Support Vector Regression and Texture-Based Features |
title_fullStr |
Age Estimation on Human Face Image Using Support Vector Regression and Texture-Based Features |
title_full_unstemmed |
Age Estimation on Human Face Image Using Support Vector Regression and Texture-Based Features |
title_sort |
age estimation on human face image using support vector regression and texture-based features |
publisher |
The Science and Information (SAI) |
publishDate |
2022 |
url |
https://repository.ugm.ac.id/279161/1/Amelia_PA.pdf https://repository.ugm.ac.id/279161/ https://www.ijacsa.thesai.org |
_version_ |
1781794704130572288 |