Loading…

Superpixel-based principal feature clustering annotation method for dual-phase microstructure segmentation

Metallographic analysis is one of the most commonly used techniques by materials scientists for studying metal materials. The deep learning methods, which have been widely applied in metallographic images analysis, demonstrate excellent performance in this task. However, the optimization of deep lea...

Full description

Saved in:
Bibliographic Details
Published in:Materials characterization 2024-12, Vol.218, p.114523, Article 114523
Main Authors: Lin, Shuanglan, Xu, Lei, Guo, Zhixing, Zhang, Dingcheng, Zeng, Pangwei, Tang, Yuexin, Pei, Hongliang
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites cdi_FETCH-LOGICAL-c187t-54a216ee066faff682d734fbe29d411fe6b9bf0a996bd50778291d45e0617b0f3
container_end_page
container_issue
container_start_page 114523
container_title Materials characterization
container_volume 218
creator Lin, Shuanglan
Xu, Lei
Guo, Zhixing
Zhang, Dingcheng
Zeng, Pangwei
Tang, Yuexin
Pei, Hongliang
description Metallographic analysis is one of the most commonly used techniques by materials scientists for studying metal materials. The deep learning methods, which have been widely applied in metallographic images analysis, demonstrate excellent performance in this task. However, the optimization of deep learning models often relies on a substantial amount of accurately labeled samples for effective supervision. To address this issue, this paper proposes a novel automatic annotation method based on brightness and spatial distribution which is suitable for deep learning-based segmentation of optical dual-phase metallographic microstructure. The proposed automatic annotated method includes the superpixel segmentation, principal feature extraction, and clustering algorithm therefore it is referred as the superpixel-based principal feature clustering annotation (SPFCA) method. SPFCA employs discriminative criteria similar to those used by metallurgists to differentiate between metallographic structures. Furthermore, it can mitigate the occasional errors inherent in manual annotation, leading to improved performance compared to models trained with expert annotations. Experimental validation was conducted using four self-built datasets with different image qualities to test the performance of models from different perspective. Initially, hyperparameter optimization for the SPFCA method tailored to our dataset was performed. Subsequently, SPFCA was utilized to guide the optimization of the convolutional neural network employed for segmentation. The results demonstrate that the segmentation model optimized with SPFCA guidance achieved an F1 score of 0.9226 in the single dataset without the need for manual labeling, surpassing the segmentation models optimized with expert annotations. [Display omitted] •The advancement of deep learning has facilitated the quantitative analysis of metallographic images.•We propose a novel annotation method suitable for learning-based segmentation in dual-phase microstructures.•Our method has a similar judgment mechnism with metallurgists distinguishing dual-phase microstructures.•This method operates without manual intervention and reduces errors that arise from the inaccuracy of experts.•The performance of the model, guided by our method, exceeds that of models trained with manually labeled data.
doi_str_mv 10.1016/j.matchar.2024.114523
format article
fullrecord <record><control><sourceid>elsevier_cross</sourceid><recordid>TN_cdi_crossref_primary_10_1016_j_matchar_2024_114523</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S1044580324009045</els_id><sourcerecordid>S1044580324009045</sourcerecordid><originalsourceid>FETCH-LOGICAL-c187t-54a216ee066faff682d734fbe29d411fe6b9bf0a996bd50778291d45e0617b0f3</originalsourceid><addsrcrecordid>eNqFkMtKxDAUhrNQcLw8gpAXaM1p07RdiQzeYMCFug5pcjKT0htJKvr2duzsXR344fv5z0fILbAUGIi7Nu1V1Afl04xlPAXgRZafkQ0wzpOiYvkFuQyhZYyJCsoNad_nCf3kvrFLGhXQ0Mm7QbtJddSiirNHqrs5RFziPVXDMEYV3TjQHuNhNNSOnppZdcl0WHDaO-3HEP2s_9CA-x6Hlbgm51Z1AW9O94p8Pj1-bF-S3dvz6_Zhl2ioypgUXGUgEJkQVlkrqsyUObcNZrXhABZFUzeWqboWjSlYWVZZDYYXCwBlw2x-RYq197gkeLRyealX_kcCk0dJspUnSfIoSa6SFu5-5XAZ9-XQy6AdDhqN86ijNKP7p-EXJMB4ig</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Superpixel-based principal feature clustering annotation method for dual-phase microstructure segmentation</title><source>ScienceDirect Freedom Collection 2022-2024</source><creator>Lin, Shuanglan ; Xu, Lei ; Guo, Zhixing ; Zhang, Dingcheng ; Zeng, Pangwei ; Tang, Yuexin ; Pei, Hongliang</creator><creatorcontrib>Lin, Shuanglan ; Xu, Lei ; Guo, Zhixing ; Zhang, Dingcheng ; Zeng, Pangwei ; Tang, Yuexin ; Pei, Hongliang</creatorcontrib><description>Metallographic analysis is one of the most commonly used techniques by materials scientists for studying metal materials. The deep learning methods, which have been widely applied in metallographic images analysis, demonstrate excellent performance in this task. However, the optimization of deep learning models often relies on a substantial amount of accurately labeled samples for effective supervision. To address this issue, this paper proposes a novel automatic annotation method based on brightness and spatial distribution which is suitable for deep learning-based segmentation of optical dual-phase metallographic microstructure. The proposed automatic annotated method includes the superpixel segmentation, principal feature extraction, and clustering algorithm therefore it is referred as the superpixel-based principal feature clustering annotation (SPFCA) method. SPFCA employs discriminative criteria similar to those used by metallurgists to differentiate between metallographic structures. Furthermore, it can mitigate the occasional errors inherent in manual annotation, leading to improved performance compared to models trained with expert annotations. Experimental validation was conducted using four self-built datasets with different image qualities to test the performance of models from different perspective. Initially, hyperparameter optimization for the SPFCA method tailored to our dataset was performed. Subsequently, SPFCA was utilized to guide the optimization of the convolutional neural network employed for segmentation. The results demonstrate that the segmentation model optimized with SPFCA guidance achieved an F1 score of 0.9226 in the single dataset without the need for manual labeling, surpassing the segmentation models optimized with expert annotations. [Display omitted] •The advancement of deep learning has facilitated the quantitative analysis of metallographic images.•We propose a novel annotation method suitable for learning-based segmentation in dual-phase microstructures.•Our method has a similar judgment mechnism with metallurgists distinguishing dual-phase microstructures.•This method operates without manual intervention and reduces errors that arise from the inaccuracy of experts.•The performance of the model, guided by our method, exceeds that of models trained with manually labeled data.</description><identifier>ISSN: 1044-5803</identifier><identifier>DOI: 10.1016/j.matchar.2024.114523</identifier><language>eng</language><publisher>Elsevier Inc</publisher><subject>Automatical annotation ; Deep learning ; Microstructure segmentation ; Superpixel segmentation</subject><ispartof>Materials characterization, 2024-12, Vol.218, p.114523, Article 114523</ispartof><rights>2024</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c187t-54a216ee066faff682d734fbe29d411fe6b9bf0a996bd50778291d45e0617b0f3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Lin, Shuanglan</creatorcontrib><creatorcontrib>Xu, Lei</creatorcontrib><creatorcontrib>Guo, Zhixing</creatorcontrib><creatorcontrib>Zhang, Dingcheng</creatorcontrib><creatorcontrib>Zeng, Pangwei</creatorcontrib><creatorcontrib>Tang, Yuexin</creatorcontrib><creatorcontrib>Pei, Hongliang</creatorcontrib><title>Superpixel-based principal feature clustering annotation method for dual-phase microstructure segmentation</title><title>Materials characterization</title><description>Metallographic analysis is one of the most commonly used techniques by materials scientists for studying metal materials. The deep learning methods, which have been widely applied in metallographic images analysis, demonstrate excellent performance in this task. However, the optimization of deep learning models often relies on a substantial amount of accurately labeled samples for effective supervision. To address this issue, this paper proposes a novel automatic annotation method based on brightness and spatial distribution which is suitable for deep learning-based segmentation of optical dual-phase metallographic microstructure. The proposed automatic annotated method includes the superpixel segmentation, principal feature extraction, and clustering algorithm therefore it is referred as the superpixel-based principal feature clustering annotation (SPFCA) method. SPFCA employs discriminative criteria similar to those used by metallurgists to differentiate between metallographic structures. Furthermore, it can mitigate the occasional errors inherent in manual annotation, leading to improved performance compared to models trained with expert annotations. Experimental validation was conducted using four self-built datasets with different image qualities to test the performance of models from different perspective. Initially, hyperparameter optimization for the SPFCA method tailored to our dataset was performed. Subsequently, SPFCA was utilized to guide the optimization of the convolutional neural network employed for segmentation. The results demonstrate that the segmentation model optimized with SPFCA guidance achieved an F1 score of 0.9226 in the single dataset without the need for manual labeling, surpassing the segmentation models optimized with expert annotations. [Display omitted] •The advancement of deep learning has facilitated the quantitative analysis of metallographic images.•We propose a novel annotation method suitable for learning-based segmentation in dual-phase microstructures.•Our method has a similar judgment mechnism with metallurgists distinguishing dual-phase microstructures.•This method operates without manual intervention and reduces errors that arise from the inaccuracy of experts.•The performance of the model, guided by our method, exceeds that of models trained with manually labeled data.</description><subject>Automatical annotation</subject><subject>Deep learning</subject><subject>Microstructure segmentation</subject><subject>Superpixel segmentation</subject><issn>1044-5803</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNqFkMtKxDAUhrNQcLw8gpAXaM1p07RdiQzeYMCFug5pcjKT0htJKvr2duzsXR344fv5z0fILbAUGIi7Nu1V1Afl04xlPAXgRZafkQ0wzpOiYvkFuQyhZYyJCsoNad_nCf3kvrFLGhXQ0Mm7QbtJddSiirNHqrs5RFziPVXDMEYV3TjQHuNhNNSOnppZdcl0WHDaO-3HEP2s_9CA-x6Hlbgm51Z1AW9O94p8Pj1-bF-S3dvz6_Zhl2ioypgUXGUgEJkQVlkrqsyUObcNZrXhABZFUzeWqboWjSlYWVZZDYYXCwBlw2x-RYq197gkeLRyealX_kcCk0dJspUnSfIoSa6SFu5-5XAZ9-XQy6AdDhqN86ijNKP7p-EXJMB4ig</recordid><startdate>202412</startdate><enddate>202412</enddate><creator>Lin, Shuanglan</creator><creator>Xu, Lei</creator><creator>Guo, Zhixing</creator><creator>Zhang, Dingcheng</creator><creator>Zeng, Pangwei</creator><creator>Tang, Yuexin</creator><creator>Pei, Hongliang</creator><general>Elsevier Inc</general><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>202412</creationdate><title>Superpixel-based principal feature clustering annotation method for dual-phase microstructure segmentation</title><author>Lin, Shuanglan ; Xu, Lei ; Guo, Zhixing ; Zhang, Dingcheng ; Zeng, Pangwei ; Tang, Yuexin ; Pei, Hongliang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c187t-54a216ee066faff682d734fbe29d411fe6b9bf0a996bd50778291d45e0617b0f3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Automatical annotation</topic><topic>Deep learning</topic><topic>Microstructure segmentation</topic><topic>Superpixel segmentation</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Lin, Shuanglan</creatorcontrib><creatorcontrib>Xu, Lei</creatorcontrib><creatorcontrib>Guo, Zhixing</creatorcontrib><creatorcontrib>Zhang, Dingcheng</creatorcontrib><creatorcontrib>Zeng, Pangwei</creatorcontrib><creatorcontrib>Tang, Yuexin</creatorcontrib><creatorcontrib>Pei, Hongliang</creatorcontrib><collection>CrossRef</collection><jtitle>Materials characterization</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Lin, Shuanglan</au><au>Xu, Lei</au><au>Guo, Zhixing</au><au>Zhang, Dingcheng</au><au>Zeng, Pangwei</au><au>Tang, Yuexin</au><au>Pei, Hongliang</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Superpixel-based principal feature clustering annotation method for dual-phase microstructure segmentation</atitle><jtitle>Materials characterization</jtitle><date>2024-12</date><risdate>2024</risdate><volume>218</volume><spage>114523</spage><pages>114523-</pages><artnum>114523</artnum><issn>1044-5803</issn><abstract>Metallographic analysis is one of the most commonly used techniques by materials scientists for studying metal materials. The deep learning methods, which have been widely applied in metallographic images analysis, demonstrate excellent performance in this task. However, the optimization of deep learning models often relies on a substantial amount of accurately labeled samples for effective supervision. To address this issue, this paper proposes a novel automatic annotation method based on brightness and spatial distribution which is suitable for deep learning-based segmentation of optical dual-phase metallographic microstructure. The proposed automatic annotated method includes the superpixel segmentation, principal feature extraction, and clustering algorithm therefore it is referred as the superpixel-based principal feature clustering annotation (SPFCA) method. SPFCA employs discriminative criteria similar to those used by metallurgists to differentiate between metallographic structures. Furthermore, it can mitigate the occasional errors inherent in manual annotation, leading to improved performance compared to models trained with expert annotations. Experimental validation was conducted using four self-built datasets with different image qualities to test the performance of models from different perspective. Initially, hyperparameter optimization for the SPFCA method tailored to our dataset was performed. Subsequently, SPFCA was utilized to guide the optimization of the convolutional neural network employed for segmentation. The results demonstrate that the segmentation model optimized with SPFCA guidance achieved an F1 score of 0.9226 in the single dataset without the need for manual labeling, surpassing the segmentation models optimized with expert annotations. [Display omitted] •The advancement of deep learning has facilitated the quantitative analysis of metallographic images.•We propose a novel annotation method suitable for learning-based segmentation in dual-phase microstructures.•Our method has a similar judgment mechnism with metallurgists distinguishing dual-phase microstructures.•This method operates without manual intervention and reduces errors that arise from the inaccuracy of experts.•The performance of the model, guided by our method, exceeds that of models trained with manually labeled data.</abstract><pub>Elsevier Inc</pub><doi>10.1016/j.matchar.2024.114523</doi></addata></record>
fulltext fulltext
identifier ISSN: 1044-5803
ispartof Materials characterization, 2024-12, Vol.218, p.114523, Article 114523
issn 1044-5803
language eng
recordid cdi_crossref_primary_10_1016_j_matchar_2024_114523
source ScienceDirect Freedom Collection 2022-2024
subjects Automatical annotation
Deep learning
Microstructure segmentation
Superpixel segmentation
title Superpixel-based principal feature clustering annotation method for dual-phase microstructure segmentation
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T03%3A02%3A34IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-elsevier_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Superpixel-based%20principal%20feature%20clustering%20annotation%20method%20for%20dual-phase%20microstructure%20segmentation&rft.jtitle=Materials%20characterization&rft.au=Lin,%20Shuanglan&rft.date=2024-12&rft.volume=218&rft.spage=114523&rft.pages=114523-&rft.artnum=114523&rft.issn=1044-5803&rft_id=info:doi/10.1016/j.matchar.2024.114523&rft_dat=%3Celsevier_cross%3ES1044580324009045%3C/elsevier_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c187t-54a216ee066faff682d734fbe29d411fe6b9bf0a996bd50778291d45e0617b0f3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true