Advanced Steel Microstructural Classification by Deep Learning Methods View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2018-02-01

AUTHORS

Seyed Majid Azimi, Dominik Britz, Michael Engstler, Mario Fritz, Frank Mücklich

ABSTRACT

The inner structure of a material is called microstructure. It stores the genesis of a material and determines all its physical and chemical properties. While microstructural characterization is widely spread and well known, the microstructural classification is mostly done manually by human experts, which gives rise to uncertainties due to subjectivity. Since the microstructure could be a combination of different phases or constituents with complex substructures its automatic classification is very challenging and only a few prior studies exist. Prior works focused on designed and engineered features by experts and classified microstructures separately from the feature extraction step. Recently, Deep Learning methods have shown strong performance in vision applications by learning the features from data together with the classification step. In this work, we propose a Deep Learning method for microstructural classification in the examples of certain microstructural constituents of low carbon steel. This novel method employs pixel-wise segmentation via Fully Convolutional Neural Network (FCNN) accompanied by a max-voting scheme. Our system achieves 93.94% classification accuracy, drastically outperforming the state-of-the-art method of 48.89% accuracy. Beyond the strong performance of our method, this line of research offers a more robust and first of all objective way for the difficult task of steel quality appreciation. More... »

PAGES

2128

Identifiers

URI

http://scigraph.springernature.com/pub.10.1038/s41598-018-20037-5

DOI

http://dx.doi.org/10.1038/s41598-018-20037-5

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1100671529

PUBMED

https://www.ncbi.nlm.nih.gov/pubmed/29391406


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Artificial Intelligence and Image Processing", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "German Aerospace Center (DLR), Remote Sensing Technology Institute, We\u00dfling, Germany", 
          "id": "http://www.grid.ac/institutes/grid.7551.6", 
          "name": [
            "Max Planck Institute for Informatics, Computer Vision and Multimodal Computing, Saarbr\u00fccken, Germany", 
            "Material Engineering Center Saarland, Saarbr\u00fccken, Germany", 
            "German Aerospace Center (DLR), Remote Sensing Technology Institute, We\u00dfling, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Azimi", 
        "givenName": "Seyed Majid", 
        "id": "sg:person.015414377070.27", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015414377070.27"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Saarland University, Chair of Functional Materials, Saarbr\u00fccken, Germany", 
          "id": "http://www.grid.ac/institutes/grid.11749.3a", 
          "name": [
            "Material Engineering Center Saarland, Saarbr\u00fccken, Germany", 
            "Saarland University, Chair of Functional Materials, Saarbr\u00fccken, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Britz", 
        "givenName": "Dominik", 
        "id": "sg:person.010565543043.06", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010565543043.06"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Saarland University, Chair of Functional Materials, Saarbr\u00fccken, Germany", 
          "id": "http://www.grid.ac/institutes/grid.11749.3a", 
          "name": [
            "Material Engineering Center Saarland, Saarbr\u00fccken, Germany", 
            "Saarland University, Chair of Functional Materials, Saarbr\u00fccken, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Engstler", 
        "givenName": "Michael", 
        "id": "sg:person.016164270464.07", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016164270464.07"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Max Planck Institute for Informatics, Computer Vision and Multimodal Computing, Saarbr\u00fccken, Germany", 
          "id": "http://www.grid.ac/institutes/grid.419528.3", 
          "name": [
            "Max Planck Institute for Informatics, Computer Vision and Multimodal Computing, Saarbr\u00fccken, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Fritz", 
        "givenName": "Mario", 
        "id": "sg:person.013361072755.17", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013361072755.17"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Saarland University, Chair of Functional Materials, Saarbr\u00fccken, Germany", 
          "id": "http://www.grid.ac/institutes/grid.11749.3a", 
          "name": [
            "Material Engineering Center Saarland, Saarbr\u00fccken, Germany", 
            "Saarland University, Chair of Functional Materials, Saarbr\u00fccken, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "M\u00fccklich", 
        "givenName": "Frank", 
        "id": "sg:person.0677046737.02", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0677046737.02"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1007/bf00344251", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1016635886", 
          "https://doi.org/10.1007/bf00344251"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/323533a0", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1018367015", 
          "https://doi.org/10.1038/323533a0"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2018-02-01", 
    "datePublishedReg": "2018-02-01", 
    "description": "The inner structure of a material is called microstructure. It stores the genesis of a material and determines all its physical and chemical properties. While microstructural characterization is widely spread and well known, the microstructural classification is mostly done manually by human experts, which gives rise to uncertainties due to subjectivity. Since the microstructure could be a combination of different phases or constituents with complex substructures its automatic classification is very challenging and only a few prior studies exist. Prior works focused on designed and engineered features by experts and classified microstructures separately from the feature extraction step. Recently, Deep Learning methods have shown strong performance in vision applications by learning the features from data together with the classification step. In this work, we propose a Deep Learning method for microstructural classification in the examples of certain microstructural constituents of low carbon steel. This novel method employs pixel-wise segmentation via Fully Convolutional Neural Network (FCNN) accompanied by a max-voting scheme. Our system achieves 93.94% classification accuracy, drastically outperforming the state-of-the-art method of 48.89% accuracy. Beyond the strong performance of our method, this line of research offers a more robust and first of all objective way for the difficult task of steel quality appreciation.", 
    "genre": "article", 
    "id": "sg:pub.10.1038/s41598-018-20037-5", 
    "isAccessibleForFree": true, 
    "isPartOf": [
      {
        "id": "sg:journal.1045337", 
        "issn": [
          "2045-2322"
        ], 
        "name": "Scientific Reports", 
        "publisher": "Springer Nature", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "1", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "8"
      }
    ], 
    "keywords": [
      "deep learning methods", 
      "Fully Convolutional Neural Network", 
      "learning methods", 
      "microstructural classification", 
      "convolutional neural network", 
      "pixel-wise segmentation", 
      "feature extraction step", 
      "strong performance", 
      "vision applications", 
      "human experts", 
      "automatic classification", 
      "neural network", 
      "classification step", 
      "art methods", 
      "classification accuracy", 
      "prior work", 
      "difficult task", 
      "classification", 
      "novel method", 
      "accuracy", 
      "segmentation", 
      "line of research", 
      "experts", 
      "objective way", 
      "extraction step", 
      "network", 
      "performance", 
      "task", 
      "features", 
      "scheme", 
      "method", 
      "work", 
      "step", 
      "applications", 
      "system", 
      "inner structure", 
      "way", 
      "example", 
      "complex substructure", 
      "different phases", 
      "uncertainty", 
      "data", 
      "research", 
      "subjectivity", 
      "state", 
      "prior studies", 
      "low carbon steel", 
      "combination", 
      "microstructural constituents", 
      "carbon steel", 
      "structure", 
      "microstructural characterization", 
      "substructure", 
      "microstructure", 
      "phase", 
      "lines", 
      "chemical properties", 
      "steel", 
      "materials", 
      "rise", 
      "properties", 
      "study", 
      "appreciation", 
      "characterization", 
      "constituents", 
      "genesis"
    ], 
    "name": "Advanced Steel Microstructural Classification by Deep Learning Methods", 
    "pagination": "2128", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1100671529"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1038/s41598-018-20037-5"
        ]
      }, 
      {
        "name": "pubmed_id", 
        "type": "PropertyValue", 
        "value": [
          "29391406"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1038/s41598-018-20037-5", 
      "https://app.dimensions.ai/details/publication/pub.1100671529"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2022-12-01T06:38", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20221201/entities/gbq_results/article/article_781.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://doi.org/10.1038/s41598-018-20037-5"
  }
]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1038/s41598-018-20037-5'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1038/s41598-018-20037-5'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1038/s41598-018-20037-5'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1038/s41598-018-20037-5'


 

This table displays all metadata directly associated to this object as RDF triples.

171 TRIPLES      21 PREDICATES      93 URIs      83 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1038/s41598-018-20037-5 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N528f5a71311b49458c9cef2f29a619d4
4 schema:citation sg:pub.10.1007/bf00344251
5 sg:pub.10.1038/323533a0
6 schema:datePublished 2018-02-01
7 schema:datePublishedReg 2018-02-01
8 schema:description The inner structure of a material is called microstructure. It stores the genesis of a material and determines all its physical and chemical properties. While microstructural characterization is widely spread and well known, the microstructural classification is mostly done manually by human experts, which gives rise to uncertainties due to subjectivity. Since the microstructure could be a combination of different phases or constituents with complex substructures its automatic classification is very challenging and only a few prior studies exist. Prior works focused on designed and engineered features by experts and classified microstructures separately from the feature extraction step. Recently, Deep Learning methods have shown strong performance in vision applications by learning the features from data together with the classification step. In this work, we propose a Deep Learning method for microstructural classification in the examples of certain microstructural constituents of low carbon steel. This novel method employs pixel-wise segmentation via Fully Convolutional Neural Network (FCNN) accompanied by a max-voting scheme. Our system achieves 93.94% classification accuracy, drastically outperforming the state-of-the-art method of 48.89% accuracy. Beyond the strong performance of our method, this line of research offers a more robust and first of all objective way for the difficult task of steel quality appreciation.
9 schema:genre article
10 schema:isAccessibleForFree true
11 schema:isPartOf N213a5d9dd5934705bd8ede1a0f59917f
12 Ne166a0a0597c457c9da08c7d16e52e52
13 sg:journal.1045337
14 schema:keywords Fully Convolutional Neural Network
15 accuracy
16 applications
17 appreciation
18 art methods
19 automatic classification
20 carbon steel
21 characterization
22 chemical properties
23 classification
24 classification accuracy
25 classification step
26 combination
27 complex substructure
28 constituents
29 convolutional neural network
30 data
31 deep learning methods
32 different phases
33 difficult task
34 example
35 experts
36 extraction step
37 feature extraction step
38 features
39 genesis
40 human experts
41 inner structure
42 learning methods
43 line of research
44 lines
45 low carbon steel
46 materials
47 method
48 microstructural characterization
49 microstructural classification
50 microstructural constituents
51 microstructure
52 network
53 neural network
54 novel method
55 objective way
56 performance
57 phase
58 pixel-wise segmentation
59 prior studies
60 prior work
61 properties
62 research
63 rise
64 scheme
65 segmentation
66 state
67 steel
68 step
69 strong performance
70 structure
71 study
72 subjectivity
73 substructure
74 system
75 task
76 uncertainty
77 vision applications
78 way
79 work
80 schema:name Advanced Steel Microstructural Classification by Deep Learning Methods
81 schema:pagination 2128
82 schema:productId N61eb5f084bd244839db24eb8694af717
83 N66acde3cf68f44bdad8248d78fc84aef
84 Nb3848ea789ae434ea01f097bf3078470
85 schema:sameAs https://app.dimensions.ai/details/publication/pub.1100671529
86 https://doi.org/10.1038/s41598-018-20037-5
87 schema:sdDatePublished 2022-12-01T06:38
88 schema:sdLicense https://scigraph.springernature.com/explorer/license/
89 schema:sdPublisher N5d6e0378a0f2410d9ed3b4d6171422b2
90 schema:url https://doi.org/10.1038/s41598-018-20037-5
91 sgo:license sg:explorer/license/
92 sgo:sdDataset articles
93 rdf:type schema:ScholarlyArticle
94 N213a5d9dd5934705bd8ede1a0f59917f schema:volumeNumber 8
95 rdf:type schema:PublicationVolume
96 N4f69c913ca7d4b54bd882e4010f2edbf rdf:first sg:person.016164270464.07
97 rdf:rest N9fb73c84ee454660a336e8808f689297
98 N528f5a71311b49458c9cef2f29a619d4 rdf:first sg:person.015414377070.27
99 rdf:rest N9d707be5b7c64ee5aa3b2adcecadb73e
100 N5d6e0378a0f2410d9ed3b4d6171422b2 schema:name Springer Nature - SN SciGraph project
101 rdf:type schema:Organization
102 N61eb5f084bd244839db24eb8694af717 schema:name doi
103 schema:value 10.1038/s41598-018-20037-5
104 rdf:type schema:PropertyValue
105 N66acde3cf68f44bdad8248d78fc84aef schema:name pubmed_id
106 schema:value 29391406
107 rdf:type schema:PropertyValue
108 N68a6194c7f9c44f7882298d12a7a69e4 rdf:first sg:person.0677046737.02
109 rdf:rest rdf:nil
110 N9d707be5b7c64ee5aa3b2adcecadb73e rdf:first sg:person.010565543043.06
111 rdf:rest N4f69c913ca7d4b54bd882e4010f2edbf
112 N9fb73c84ee454660a336e8808f689297 rdf:first sg:person.013361072755.17
113 rdf:rest N68a6194c7f9c44f7882298d12a7a69e4
114 Nb3848ea789ae434ea01f097bf3078470 schema:name dimensions_id
115 schema:value pub.1100671529
116 rdf:type schema:PropertyValue
117 Ne166a0a0597c457c9da08c7d16e52e52 schema:issueNumber 1
118 rdf:type schema:PublicationIssue
119 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
120 schema:name Information and Computing Sciences
121 rdf:type schema:DefinedTerm
122 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
123 schema:name Artificial Intelligence and Image Processing
124 rdf:type schema:DefinedTerm
125 sg:journal.1045337 schema:issn 2045-2322
126 schema:name Scientific Reports
127 schema:publisher Springer Nature
128 rdf:type schema:Periodical
129 sg:person.010565543043.06 schema:affiliation grid-institutes:grid.11749.3a
130 schema:familyName Britz
131 schema:givenName Dominik
132 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010565543043.06
133 rdf:type schema:Person
134 sg:person.013361072755.17 schema:affiliation grid-institutes:grid.419528.3
135 schema:familyName Fritz
136 schema:givenName Mario
137 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013361072755.17
138 rdf:type schema:Person
139 sg:person.015414377070.27 schema:affiliation grid-institutes:grid.7551.6
140 schema:familyName Azimi
141 schema:givenName Seyed Majid
142 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015414377070.27
143 rdf:type schema:Person
144 sg:person.016164270464.07 schema:affiliation grid-institutes:grid.11749.3a
145 schema:familyName Engstler
146 schema:givenName Michael
147 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016164270464.07
148 rdf:type schema:Person
149 sg:person.0677046737.02 schema:affiliation grid-institutes:grid.11749.3a
150 schema:familyName Mücklich
151 schema:givenName Frank
152 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0677046737.02
153 rdf:type schema:Person
154 sg:pub.10.1007/bf00344251 schema:sameAs https://app.dimensions.ai/details/publication/pub.1016635886
155 https://doi.org/10.1007/bf00344251
156 rdf:type schema:CreativeWork
157 sg:pub.10.1038/323533a0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1018367015
158 https://doi.org/10.1038/323533a0
159 rdf:type schema:CreativeWork
160 grid-institutes:grid.11749.3a schema:alternateName Saarland University, Chair of Functional Materials, Saarbrücken, Germany
161 schema:name Material Engineering Center Saarland, Saarbrücken, Germany
162 Saarland University, Chair of Functional Materials, Saarbrücken, Germany
163 rdf:type schema:Organization
164 grid-institutes:grid.419528.3 schema:alternateName Max Planck Institute for Informatics, Computer Vision and Multimodal Computing, Saarbrücken, Germany
165 schema:name Max Planck Institute for Informatics, Computer Vision and Multimodal Computing, Saarbrücken, Germany
166 rdf:type schema:Organization
167 grid-institutes:grid.7551.6 schema:alternateName German Aerospace Center (DLR), Remote Sensing Technology Institute, Weßling, Germany
168 schema:name German Aerospace Center (DLR), Remote Sensing Technology Institute, Weßling, Germany
169 Material Engineering Center Saarland, Saarbrücken, Germany
170 Max Planck Institute for Informatics, Computer Vision and Multimodal Computing, Saarbrücken, Germany
171 rdf:type schema:Organization
 




Preview window. Press ESC to close (or click here)


...