Age detection by optimizing the structure of layers and neurons in the neural network

Age detection is a fundamental task in computer vision with numerous applications, from targeted advertising to security systems. This paper proposes a robust approach for age estimation based on local binary patterns to extract features associated with face images. The goal of accurately predicting...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of optics (New Delhi) 2024-04, Vol.53 (2), p.1186-1202
Hauptverfasser: Jiang, Zhenghong, Zhou, Chunrong
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 1202
container_issue 2
container_start_page 1186
container_title Journal of optics (New Delhi)
container_volume 53
creator Jiang, Zhenghong
Zhou, Chunrong
description Age detection is a fundamental task in computer vision with numerous applications, from targeted advertising to security systems. This paper proposes a robust approach for age estimation based on local binary patterns to extract features associated with face images. The goal of accurately predicting people's ages from facial images is to overcome challenges such as changes in lighting conditions, poses, and facial expressions. The proposed method uses a combination of feature extraction, feature selection, and machine learning algorithms, which we named Hybrid method. At first, facial landmarks are detected to determine the key points of the face and enable the extraction of the corresponding facial features. These features are then fed into a feature selection algorithm to identify the most distinctive ones, reducing dimensionality and increasing model efficiency. To evaluate the proposed approach, extensive experiments are conducted on benchmark datasets, including different age groups and ethnicities. The results show the effectiveness of the proposed method in achieving high accuracy and robustness in age estimation. As shown in the calculation results, the detection rate and accuracy of Hybrid method age estimation calculations are better than competing methods. For Hybrid method, the mean absolute error is 4.94 years, with a standard deviation of 4.74 years. From the point of view of average absolute error, this age estimation method is superior to other methods that have been presented to date. The proposed method for estimating the age of people has a final sensitivity of 97.2%, an accuracy of 96.8%, and a precision of 99.1%. In addition, it is stated in the specifications of the implementation system that the program can be executed in about 3.5 s, which is a suitable speed for estimating the age of people based on their face photographs.
doi_str_mv 10.1007/s12596-023-01268-w
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_3037835229</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3037835229</sourcerecordid><originalsourceid>FETCH-LOGICAL-c270t-83dd9b81d48da0baf7a7563901ccf45504450b1cdaacf4d2362b5620517750483</originalsourceid><addsrcrecordid>eNp9kE9LAzEQxYMoWLRfwFPAc3SSbDbZYyn-g4IXew7ZTbautklNspT66U1bwZunN8O89wZ-CN1QuKMA8j5RJpqaAOMEKKsV2Z2hCTSyInUDcH6cGVGK0Us0TWloQUANFEQzQcvZymHrsuvyEDxu9zhs87AZvge_wvnd4ZTj2OUxOhx6vDZ7FxM23mLvxhh8woM_2g6rWRfJuxA_r9FFb9bJTX_1Ci0fH97mz2Tx-vQyny1IxyRkori1TauorZQ10JpeGilq3gDtur4SAqpKQEs7a0zZLeM1a0XNQFApy1HxK3R76t3G8DW6lPVHGKMvLzUHLhUXjDXFxU6uLoaUouv1Ng4bE_eagj4Q1CeCuhDUR4J6V0L8FErF7Fcu_lX_k_oBcEN0Mw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3037835229</pqid></control><display><type>article</type><title>Age detection by optimizing the structure of layers and neurons in the neural network</title><source>SpringerNature Journals</source><creator>Jiang, Zhenghong ; Zhou, Chunrong</creator><creatorcontrib>Jiang, Zhenghong ; Zhou, Chunrong</creatorcontrib><description>Age detection is a fundamental task in computer vision with numerous applications, from targeted advertising to security systems. This paper proposes a robust approach for age estimation based on local binary patterns to extract features associated with face images. The goal of accurately predicting people's ages from facial images is to overcome challenges such as changes in lighting conditions, poses, and facial expressions. The proposed method uses a combination of feature extraction, feature selection, and machine learning algorithms, which we named Hybrid method. At first, facial landmarks are detected to determine the key points of the face and enable the extraction of the corresponding facial features. These features are then fed into a feature selection algorithm to identify the most distinctive ones, reducing dimensionality and increasing model efficiency. To evaluate the proposed approach, extensive experiments are conducted on benchmark datasets, including different age groups and ethnicities. The results show the effectiveness of the proposed method in achieving high accuracy and robustness in age estimation. As shown in the calculation results, the detection rate and accuracy of Hybrid method age estimation calculations are better than competing methods. For Hybrid method, the mean absolute error is 4.94 years, with a standard deviation of 4.74 years. From the point of view of average absolute error, this age estimation method is superior to other methods that have been presented to date. The proposed method for estimating the age of people has a final sensitivity of 97.2%, an accuracy of 96.8%, and a precision of 99.1%. In addition, it is stated in the specifications of the implementation system that the program can be executed in about 3.5 s, which is a suitable speed for estimating the age of people based on their face photographs.</description><identifier>ISSN: 0972-8821</identifier><identifier>EISSN: 0974-6900</identifier><identifier>DOI: 10.1007/s12596-023-01268-w</identifier><language>eng</language><publisher>New Delhi: Springer India</publisher><subject>Accuracy ; Age ; Algorithms ; Chronology ; Computer vision ; Estimation ; Feature extraction ; Feature selection ; Lasers ; Machine learning ; Neural networks ; Optical Devices ; Optics ; Photonics ; Physics ; Physics and Astronomy ; Research Article ; Security systems</subject><ispartof>Journal of optics (New Delhi), 2024-04, Vol.53 (2), p.1186-1202</ispartof><rights>The Author(s), under exclusive licence to The Optical Society of India 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c270t-83dd9b81d48da0baf7a7563901ccf45504450b1cdaacf4d2362b5620517750483</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s12596-023-01268-w$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s12596-023-01268-w$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,780,784,27924,27925,41488,42557,51319</link.rule.ids></links><search><creatorcontrib>Jiang, Zhenghong</creatorcontrib><creatorcontrib>Zhou, Chunrong</creatorcontrib><title>Age detection by optimizing the structure of layers and neurons in the neural network</title><title>Journal of optics (New Delhi)</title><addtitle>J Opt</addtitle><description>Age detection is a fundamental task in computer vision with numerous applications, from targeted advertising to security systems. This paper proposes a robust approach for age estimation based on local binary patterns to extract features associated with face images. The goal of accurately predicting people's ages from facial images is to overcome challenges such as changes in lighting conditions, poses, and facial expressions. The proposed method uses a combination of feature extraction, feature selection, and machine learning algorithms, which we named Hybrid method. At first, facial landmarks are detected to determine the key points of the face and enable the extraction of the corresponding facial features. These features are then fed into a feature selection algorithm to identify the most distinctive ones, reducing dimensionality and increasing model efficiency. To evaluate the proposed approach, extensive experiments are conducted on benchmark datasets, including different age groups and ethnicities. The results show the effectiveness of the proposed method in achieving high accuracy and robustness in age estimation. As shown in the calculation results, the detection rate and accuracy of Hybrid method age estimation calculations are better than competing methods. For Hybrid method, the mean absolute error is 4.94 years, with a standard deviation of 4.74 years. From the point of view of average absolute error, this age estimation method is superior to other methods that have been presented to date. The proposed method for estimating the age of people has a final sensitivity of 97.2%, an accuracy of 96.8%, and a precision of 99.1%. In addition, it is stated in the specifications of the implementation system that the program can be executed in about 3.5 s, which is a suitable speed for estimating the age of people based on their face photographs.</description><subject>Accuracy</subject><subject>Age</subject><subject>Algorithms</subject><subject>Chronology</subject><subject>Computer vision</subject><subject>Estimation</subject><subject>Feature extraction</subject><subject>Feature selection</subject><subject>Lasers</subject><subject>Machine learning</subject><subject>Neural networks</subject><subject>Optical Devices</subject><subject>Optics</subject><subject>Photonics</subject><subject>Physics</subject><subject>Physics and Astronomy</subject><subject>Research Article</subject><subject>Security systems</subject><issn>0972-8821</issn><issn>0974-6900</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNp9kE9LAzEQxYMoWLRfwFPAc3SSbDbZYyn-g4IXew7ZTbautklNspT66U1bwZunN8O89wZ-CN1QuKMA8j5RJpqaAOMEKKsV2Z2hCTSyInUDcH6cGVGK0Us0TWloQUANFEQzQcvZymHrsuvyEDxu9zhs87AZvge_wvnd4ZTj2OUxOhx6vDZ7FxM23mLvxhh8woM_2g6rWRfJuxA_r9FFb9bJTX_1Ci0fH97mz2Tx-vQyny1IxyRkori1TauorZQ10JpeGilq3gDtur4SAqpKQEs7a0zZLeM1a0XNQFApy1HxK3R76t3G8DW6lPVHGKMvLzUHLhUXjDXFxU6uLoaUouv1Ng4bE_eagj4Q1CeCuhDUR4J6V0L8FErF7Fcu_lX_k_oBcEN0Mw</recordid><startdate>20240401</startdate><enddate>20240401</enddate><creator>Jiang, Zhenghong</creator><creator>Zhou, Chunrong</creator><general>Springer India</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>20240401</creationdate><title>Age detection by optimizing the structure of layers and neurons in the neural network</title><author>Jiang, Zhenghong ; Zhou, Chunrong</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c270t-83dd9b81d48da0baf7a7563901ccf45504450b1cdaacf4d2362b5620517750483</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Accuracy</topic><topic>Age</topic><topic>Algorithms</topic><topic>Chronology</topic><topic>Computer vision</topic><topic>Estimation</topic><topic>Feature extraction</topic><topic>Feature selection</topic><topic>Lasers</topic><topic>Machine learning</topic><topic>Neural networks</topic><topic>Optical Devices</topic><topic>Optics</topic><topic>Photonics</topic><topic>Physics</topic><topic>Physics and Astronomy</topic><topic>Research Article</topic><topic>Security systems</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Jiang, Zhenghong</creatorcontrib><creatorcontrib>Zhou, Chunrong</creatorcontrib><collection>CrossRef</collection><jtitle>Journal of optics (New Delhi)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Jiang, Zhenghong</au><au>Zhou, Chunrong</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Age detection by optimizing the structure of layers and neurons in the neural network</atitle><jtitle>Journal of optics (New Delhi)</jtitle><stitle>J Opt</stitle><date>2024-04-01</date><risdate>2024</risdate><volume>53</volume><issue>2</issue><spage>1186</spage><epage>1202</epage><pages>1186-1202</pages><issn>0972-8821</issn><eissn>0974-6900</eissn><abstract>Age detection is a fundamental task in computer vision with numerous applications, from targeted advertising to security systems. This paper proposes a robust approach for age estimation based on local binary patterns to extract features associated with face images. The goal of accurately predicting people's ages from facial images is to overcome challenges such as changes in lighting conditions, poses, and facial expressions. The proposed method uses a combination of feature extraction, feature selection, and machine learning algorithms, which we named Hybrid method. At first, facial landmarks are detected to determine the key points of the face and enable the extraction of the corresponding facial features. These features are then fed into a feature selection algorithm to identify the most distinctive ones, reducing dimensionality and increasing model efficiency. To evaluate the proposed approach, extensive experiments are conducted on benchmark datasets, including different age groups and ethnicities. The results show the effectiveness of the proposed method in achieving high accuracy and robustness in age estimation. As shown in the calculation results, the detection rate and accuracy of Hybrid method age estimation calculations are better than competing methods. For Hybrid method, the mean absolute error is 4.94 years, with a standard deviation of 4.74 years. From the point of view of average absolute error, this age estimation method is superior to other methods that have been presented to date. The proposed method for estimating the age of people has a final sensitivity of 97.2%, an accuracy of 96.8%, and a precision of 99.1%. In addition, it is stated in the specifications of the implementation system that the program can be executed in about 3.5 s, which is a suitable speed for estimating the age of people based on their face photographs.</abstract><cop>New Delhi</cop><pub>Springer India</pub><doi>10.1007/s12596-023-01268-w</doi><tpages>17</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0972-8821
ispartof Journal of optics (New Delhi), 2024-04, Vol.53 (2), p.1186-1202
issn 0972-8821
0974-6900
language eng
recordid cdi_proquest_journals_3037835229
source SpringerNature Journals
subjects Accuracy
Age
Algorithms
Chronology
Computer vision
Estimation
Feature extraction
Feature selection
Lasers
Machine learning
Neural networks
Optical Devices
Optics
Photonics
Physics
Physics and Astronomy
Research Article
Security systems
title Age detection by optimizing the structure of layers and neurons in the neural network
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-27T20%3A32%3A33IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Age%20detection%20by%20optimizing%20the%20structure%20of%20layers%20and%20neurons%20in%20the%20neural%20network&rft.jtitle=Journal%20of%20optics%20(New%20Delhi)&rft.au=Jiang,%20Zhenghong&rft.date=2024-04-01&rft.volume=53&rft.issue=2&rft.spage=1186&rft.epage=1202&rft.pages=1186-1202&rft.issn=0972-8821&rft.eissn=0974-6900&rft_id=info:doi/10.1007/s12596-023-01268-w&rft_dat=%3Cproquest_cross%3E3037835229%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3037835229&rft_id=info:pmid/&rfr_iscdi=true