Microstructure Cluster Analysis with Transfer Learning and Unsupervised Learning View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2018-09

AUTHORS

Andrew R. Kitahara, Elizabeth A. Holm

ABSTRACT

We apply computer vision and machine learning methods to analyze two datasets of microstructural images. A transfer learning pipeline utilizes the fully connected layer of a pre-trained convolutional neural network as the image representation. An unsupervised learning method uses the image representations to discover visually distinct clusters of images within two datasets. A minimally supervised clustering approach classifies micrographs into visually similar groups. This approach successfully classifies images both in a dataset of surface defects in steel, where the image classes are visually distinct and in a dataset of fracture surfaces that humans have difficulty classifying. We find that the unsupervised, transfer learning method gives results comparable to fully supervised, custom-built approaches. More... »

PAGES

148-156

References to SciGraph publications

  • 2015-12. ImageNet Large Scale Visual Recognition Challenge in INTERNATIONAL JOURNAL OF COMPUTER VISION
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/s40192-018-0116-9

    DOI

    http://dx.doi.org/10.1007/s40192-018-0116-9

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1106430732


    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/2008/0801", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Artificial Intelligence and Image Processing", 
            "type": "DefinedTerm"
          }, 
          {
            "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"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "Carnegie Mellon University", 
              "id": "https://www.grid.ac/institutes/grid.147455.6", 
              "name": [
                "Carnegie Mellon University, Pittsburgh, PA, USA"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Kitahara", 
            "givenName": "Andrew R.", 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Carnegie Mellon University", 
              "id": "https://www.grid.ac/institutes/grid.147455.6", 
              "name": [
                "Carnegie Mellon University, Pittsburgh, PA, USA"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Holm", 
            "givenName": "Elizabeth A.", 
            "id": "sg:person.0700236700.73", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0700236700.73"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1007/s11263-015-0816-y", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1009767488", 
              "https://doi.org/10.1007/s11263-015-0816-y"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1002/wics.101", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1012628338"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.apsusc.2013.09.002", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1030463527"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.infsof.2008.09.005", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1039058626"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1021/co200007w", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1040675653"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.7717/peerj.453", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1046599992"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1146/annurev-matsci-070214-020844", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1047503137"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/34.868684", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061157126"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.17222/mit.2015.335", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1083980993"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.actamat.2017.05.014", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1085416218"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.actamat.2017.05.014", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1085416218"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.actamat.2017.05.014", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1085416218"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.23915/distill.00007", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1092587583"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iconip.1999.844687", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093934245"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2011.6126544", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094015616"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/rteict.2016.7808140", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095568540"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2017.371", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1100060361"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.2307/2346830", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1101982469"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.2307/2346830", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1101982469"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2018.2858759", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1105796923"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2018-09", 
        "datePublishedReg": "2018-09-01", 
        "description": "We apply computer vision and machine learning methods to analyze two datasets of microstructural images. A transfer learning pipeline utilizes the fully connected layer of a pre-trained convolutional neural network as the image representation. An unsupervised learning method uses the image representations to discover visually distinct clusters of images within two datasets. A minimally supervised clustering approach classifies micrographs into visually similar groups. This approach successfully classifies images both in a dataset of surface defects in steel, where the image classes are visually distinct and in a dataset of fracture surfaces that humans have difficulty classifying. We find that the unsupervised, transfer learning method gives results comparable to fully supervised, custom-built approaches.", 
        "genre": "research_article", 
        "id": "sg:pub.10.1007/s40192-018-0116-9", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": false, 
        "isFundedItemOf": [
          {
            "id": "sg:grant.4318069", 
            "type": "MonetaryGrant"
          }
        ], 
        "isPartOf": [
          {
            "id": "sg:journal.1136615", 
            "issn": [
              "2193-9764", 
              "2193-9772"
            ], 
            "name": "Integrating Materials and Manufacturing Innovation", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "3", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "7"
          }
        ], 
        "name": "Microstructure Cluster Analysis with Transfer Learning and Unsupervised Learning", 
        "pagination": "148-156", 
        "productId": [
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "caf8742881d3bfbfb85dfbc4ba4fb60483a5014be843afea5c7326708d786644"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/s40192-018-0116-9"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1106430732"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1007/s40192-018-0116-9", 
          "https://app.dimensions.ai/details/publication/pub.1106430732"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2019-04-10T23:40", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000001_0000000264/records_8693_00000605.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "http://link.springer.com/10.1007/s40192-018-0116-9"
      }
    ]
     

    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.10.1007/s40192-018-0116-9'

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

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/s40192-018-0116-9'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s40192-018-0116-9'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s40192-018-0116-9'


     

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

    121 TRIPLES      21 PREDICATES      44 URIs      19 LITERALS      7 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/s40192-018-0116-9 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author Na3333984274545a097e1973785de7540
    4 schema:citation sg:pub.10.1007/s11263-015-0816-y
    5 https://doi.org/10.1002/wics.101
    6 https://doi.org/10.1016/j.actamat.2017.05.014
    7 https://doi.org/10.1016/j.apsusc.2013.09.002
    8 https://doi.org/10.1016/j.infsof.2008.09.005
    9 https://doi.org/10.1021/co200007w
    10 https://doi.org/10.1109/34.868684
    11 https://doi.org/10.1109/iccv.2011.6126544
    12 https://doi.org/10.1109/iccv.2017.371
    13 https://doi.org/10.1109/iconip.1999.844687
    14 https://doi.org/10.1109/rteict.2016.7808140
    15 https://doi.org/10.1109/tpami.2018.2858759
    16 https://doi.org/10.1146/annurev-matsci-070214-020844
    17 https://doi.org/10.17222/mit.2015.335
    18 https://doi.org/10.2307/2346830
    19 https://doi.org/10.23915/distill.00007
    20 https://doi.org/10.7717/peerj.453
    21 schema:datePublished 2018-09
    22 schema:datePublishedReg 2018-09-01
    23 schema:description We apply computer vision and machine learning methods to analyze two datasets of microstructural images. A transfer learning pipeline utilizes the fully connected layer of a pre-trained convolutional neural network as the image representation. An unsupervised learning method uses the image representations to discover visually distinct clusters of images within two datasets. A minimally supervised clustering approach classifies micrographs into visually similar groups. This approach successfully classifies images both in a dataset of surface defects in steel, where the image classes are visually distinct and in a dataset of fracture surfaces that humans have difficulty classifying. We find that the unsupervised, transfer learning method gives results comparable to fully supervised, custom-built approaches.
    24 schema:genre research_article
    25 schema:inLanguage en
    26 schema:isAccessibleForFree false
    27 schema:isPartOf N68707872b4ac4662ab300aa7af981f70
    28 N8efbae5cd0184bc18aafa5ce4f82f7f1
    29 sg:journal.1136615
    30 schema:name Microstructure Cluster Analysis with Transfer Learning and Unsupervised Learning
    31 schema:pagination 148-156
    32 schema:productId N264b1657b2b5408abf6ceca452606fd2
    33 N6afffc7e0cb541adbc08e930b6b67520
    34 Ne6def322d1df409cb8d2326e4a88c172
    35 schema:sameAs https://app.dimensions.ai/details/publication/pub.1106430732
    36 https://doi.org/10.1007/s40192-018-0116-9
    37 schema:sdDatePublished 2019-04-10T23:40
    38 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    39 schema:sdPublisher N0b4b9871759b43c491b216f362a9e026
    40 schema:url http://link.springer.com/10.1007/s40192-018-0116-9
    41 sgo:license sg:explorer/license/
    42 sgo:sdDataset articles
    43 rdf:type schema:ScholarlyArticle
    44 N0b4b9871759b43c491b216f362a9e026 schema:name Springer Nature - SN SciGraph project
    45 rdf:type schema:Organization
    46 N207e3ce65787488e850083b84df820b5 schema:affiliation https://www.grid.ac/institutes/grid.147455.6
    47 schema:familyName Kitahara
    48 schema:givenName Andrew R.
    49 rdf:type schema:Person
    50 N264b1657b2b5408abf6ceca452606fd2 schema:name dimensions_id
    51 schema:value pub.1106430732
    52 rdf:type schema:PropertyValue
    53 N6838e2486f6f44889bd7b3e77896309e rdf:first sg:person.0700236700.73
    54 rdf:rest rdf:nil
    55 N68707872b4ac4662ab300aa7af981f70 schema:volumeNumber 7
    56 rdf:type schema:PublicationVolume
    57 N6afffc7e0cb541adbc08e930b6b67520 schema:name doi
    58 schema:value 10.1007/s40192-018-0116-9
    59 rdf:type schema:PropertyValue
    60 N8efbae5cd0184bc18aafa5ce4f82f7f1 schema:issueNumber 3
    61 rdf:type schema:PublicationIssue
    62 Na3333984274545a097e1973785de7540 rdf:first N207e3ce65787488e850083b84df820b5
    63 rdf:rest N6838e2486f6f44889bd7b3e77896309e
    64 Ne6def322d1df409cb8d2326e4a88c172 schema:name readcube_id
    65 schema:value caf8742881d3bfbfb85dfbc4ba4fb60483a5014be843afea5c7326708d786644
    66 rdf:type schema:PropertyValue
    67 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    68 schema:name Information and Computing Sciences
    69 rdf:type schema:DefinedTerm
    70 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    71 schema:name Artificial Intelligence and Image Processing
    72 rdf:type schema:DefinedTerm
    73 sg:grant.4318069 http://pending.schema.org/fundedItem sg:pub.10.1007/s40192-018-0116-9
    74 rdf:type schema:MonetaryGrant
    75 sg:journal.1136615 schema:issn 2193-9764
    76 2193-9772
    77 schema:name Integrating Materials and Manufacturing Innovation
    78 rdf:type schema:Periodical
    79 sg:person.0700236700.73 schema:affiliation https://www.grid.ac/institutes/grid.147455.6
    80 schema:familyName Holm
    81 schema:givenName Elizabeth A.
    82 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0700236700.73
    83 rdf:type schema:Person
    84 sg:pub.10.1007/s11263-015-0816-y schema:sameAs https://app.dimensions.ai/details/publication/pub.1009767488
    85 https://doi.org/10.1007/s11263-015-0816-y
    86 rdf:type schema:CreativeWork
    87 https://doi.org/10.1002/wics.101 schema:sameAs https://app.dimensions.ai/details/publication/pub.1012628338
    88 rdf:type schema:CreativeWork
    89 https://doi.org/10.1016/j.actamat.2017.05.014 schema:sameAs https://app.dimensions.ai/details/publication/pub.1085416218
    90 rdf:type schema:CreativeWork
    91 https://doi.org/10.1016/j.apsusc.2013.09.002 schema:sameAs https://app.dimensions.ai/details/publication/pub.1030463527
    92 rdf:type schema:CreativeWork
    93 https://doi.org/10.1016/j.infsof.2008.09.005 schema:sameAs https://app.dimensions.ai/details/publication/pub.1039058626
    94 rdf:type schema:CreativeWork
    95 https://doi.org/10.1021/co200007w schema:sameAs https://app.dimensions.ai/details/publication/pub.1040675653
    96 rdf:type schema:CreativeWork
    97 https://doi.org/10.1109/34.868684 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061157126
    98 rdf:type schema:CreativeWork
    99 https://doi.org/10.1109/iccv.2011.6126544 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094015616
    100 rdf:type schema:CreativeWork
    101 https://doi.org/10.1109/iccv.2017.371 schema:sameAs https://app.dimensions.ai/details/publication/pub.1100060361
    102 rdf:type schema:CreativeWork
    103 https://doi.org/10.1109/iconip.1999.844687 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093934245
    104 rdf:type schema:CreativeWork
    105 https://doi.org/10.1109/rteict.2016.7808140 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095568540
    106 rdf:type schema:CreativeWork
    107 https://doi.org/10.1109/tpami.2018.2858759 schema:sameAs https://app.dimensions.ai/details/publication/pub.1105796923
    108 rdf:type schema:CreativeWork
    109 https://doi.org/10.1146/annurev-matsci-070214-020844 schema:sameAs https://app.dimensions.ai/details/publication/pub.1047503137
    110 rdf:type schema:CreativeWork
    111 https://doi.org/10.17222/mit.2015.335 schema:sameAs https://app.dimensions.ai/details/publication/pub.1083980993
    112 rdf:type schema:CreativeWork
    113 https://doi.org/10.2307/2346830 schema:sameAs https://app.dimensions.ai/details/publication/pub.1101982469
    114 rdf:type schema:CreativeWork
    115 https://doi.org/10.23915/distill.00007 schema:sameAs https://app.dimensions.ai/details/publication/pub.1092587583
    116 rdf:type schema:CreativeWork
    117 https://doi.org/10.7717/peerj.453 schema:sameAs https://app.dimensions.ai/details/publication/pub.1046599992
    118 rdf:type schema:CreativeWork
    119 https://www.grid.ac/institutes/grid.147455.6 schema:alternateName Carnegie Mellon University
    120 schema:name Carnegie Mellon University, Pittsburgh, PA, USA
    121 rdf:type schema:Organization
     




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


    ...