Generic Paper and Plastic Recognition by Fusion of NIR and VIS Data and Redundancy-Aware Feature Ranking View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2018-10-18

AUTHORS

Alla Serebryanyk , Matthias Zisler , Claudius Schnörr

ABSTRACT

Near infrared (NIR) spectroscopy is used in many applications to gather information about chemical composition of materials. For paper waste sorting, a small number of scores computed from NIR-spectra and assuming more or less unimodal clustered data, a pixel classifier can still be crafted by hand using knowledge about chemical properties and a reasonable amount of intuition. Additional information can be gained by visual data (VIS). However, it is not obvious what features, e.g. based on color, saturation, textured areas, are finally important for successfully separating the paper classes in feature space. Hence, a rigorous feature analysis becomes inevitable. We have chosen a generic machine-learning approach to successfully fuse NIR and VIS information. By exploiting a classification tree and a variety of additional visual features, we could increase the recognition rate to 78% for 11 classes, compared to 63% only using NIR scores. A modified feature ranking measure, which takes redundancies of features into account, allows us to analyze the importance of features and reduce them effectively. While some visual features like color saturation and hue showed to be important, some NIR scores could even be dropped. Finally, we generalize this approach to analyze raw NIR-spectra instead of score values and apply it to plastic waste sorting. More... »

PAGES

30-45

References to SciGraph publications

  • 2014-03. A critical review on waste paper sorting techniques in INTERNATIONAL JOURNAL OF ENVIRONMENTAL SCIENCE AND TECHNOLOGY
  • Book

    TITLE

    Proceedings of the Future Technologies Conference (FTC) 2018

    ISBN

    978-3-030-02685-1
    978-3-030-02686-8

    Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/978-3-030-02686-8_3

    DOI

    http://dx.doi.org/10.1007/978-3-030-02686-8_3

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1107688601


    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": "Munich University of Applied Sciences", 
              "id": "https://www.grid.ac/institutes/grid.434949.7", 
              "name": [
                "University of Applied Sciences Munich, Munich, Germany"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Serebryanyk", 
            "givenName": "Alla", 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Heidelberg University", 
              "id": "https://www.grid.ac/institutes/grid.7700.0", 
              "name": [
                "Institute of Applied Mathematics, University of Heidelberg, Heidelberg, Germany"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Zisler", 
            "givenName": "Matthias", 
            "id": "sg:person.011344614151.63", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011344614151.63"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Munich University of Applied Sciences", 
              "id": "https://www.grid.ac/institutes/grid.434949.7", 
              "name": [
                "University of Applied Sciences Munich, Munich, Germany"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Schn\u00f6rr", 
            "givenName": "Claudius", 
            "id": "sg:person.011773470723.11", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011773470723.11"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "https://doi.org/10.1016/j.patrec.2010.03.014", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1021405554"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s13762-013-0222-3", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1032595097", 
              "https://doi.org/10.1007/s13762-013-0222-3"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2018-10-18", 
        "datePublishedReg": "2018-10-18", 
        "description": "Near infrared (NIR) spectroscopy is used in many applications to gather information about chemical composition of materials. For paper waste sorting, a small number of scores computed from NIR-spectra and assuming more or less unimodal clustered data, a pixel classifier can still be crafted by hand using knowledge about chemical properties and a reasonable amount of intuition. Additional information can be gained by visual data (VIS). However, it is not obvious what features, e.g. based on color, saturation, textured areas, are finally important for successfully separating the paper classes in feature space. Hence, a rigorous feature analysis becomes inevitable. We have chosen a generic machine-learning approach to successfully fuse NIR and VIS information. By exploiting a classification tree and a variety of additional visual features, we could increase the recognition rate to 78% for 11 classes, compared to 63% only using NIR scores. A modified feature ranking measure, which takes redundancies of features into account, allows us to analyze the importance of features and reduce them effectively. While some visual features like color saturation and hue showed to be important, some NIR scores could even be dropped. Finally, we generalize this approach to analyze raw NIR-spectra instead of score values and apply it to plastic waste sorting.", 
        "editor": [
          {
            "familyName": "Arai", 
            "givenName": "Kohei", 
            "type": "Person"
          }, 
          {
            "familyName": "Bhatia", 
            "givenName": "Rahul", 
            "type": "Person"
          }, 
          {
            "familyName": "Kapoor", 
            "givenName": "Supriya", 
            "type": "Person"
          }
        ], 
        "genre": "chapter", 
        "id": "sg:pub.10.1007/978-3-030-02686-8_3", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": false, 
        "isPartOf": {
          "isbn": [
            "978-3-030-02685-1", 
            "978-3-030-02686-8"
          ], 
          "name": "Proceedings of the Future Technologies Conference (FTC) 2018", 
          "type": "Book"
        }, 
        "name": "Generic Paper and Plastic Recognition by Fusion of NIR and VIS Data and Redundancy-Aware Feature Ranking", 
        "pagination": "30-45", 
        "productId": [
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/978-3-030-02686-8_3"
            ]
          }, 
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "1b8845a8d92ed21b34f87911d0e61ce96eb1cecd03c8879cf52a94eac317bd43"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1107688601"
            ]
          }
        ], 
        "publisher": {
          "location": "Cham", 
          "name": "Springer International Publishing", 
          "type": "Organisation"
        }, 
        "sameAs": [
          "https://doi.org/10.1007/978-3-030-02686-8_3", 
          "https://app.dimensions.ai/details/publication/pub.1107688601"
        ], 
        "sdDataset": "chapters", 
        "sdDatePublished": "2019-04-16T04:39", 
        "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/v90/0000000321_0000000321/records_74936_00000000.jsonl", 
        "type": "Chapter", 
        "url": "https://link.springer.com/10.1007%2F978-3-030-02686-8_3"
      }
    ]
     

    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.10.1007/978-3-030-02686-8_3'

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

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-02686-8_3'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-02686-8_3'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-02686-8_3'


     

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

    98 TRIPLES      23 PREDICATES      28 URIs      19 LITERALS      8 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/978-3-030-02686-8_3 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author N73cf1de4928c40768d644b8ad0c73538
    4 schema:citation sg:pub.10.1007/s13762-013-0222-3
    5 https://doi.org/10.1016/j.patrec.2010.03.014
    6 schema:datePublished 2018-10-18
    7 schema:datePublishedReg 2018-10-18
    8 schema:description Near infrared (NIR) spectroscopy is used in many applications to gather information about chemical composition of materials. For paper waste sorting, a small number of scores computed from NIR-spectra and assuming more or less unimodal clustered data, a pixel classifier can still be crafted by hand using knowledge about chemical properties and a reasonable amount of intuition. Additional information can be gained by visual data (VIS). However, it is not obvious what features, e.g. based on color, saturation, textured areas, are finally important for successfully separating the paper classes in feature space. Hence, a rigorous feature analysis becomes inevitable. We have chosen a generic machine-learning approach to successfully fuse NIR and VIS information. By exploiting a classification tree and a variety of additional visual features, we could increase the recognition rate to 78% for 11 classes, compared to 63% only using NIR scores. A modified feature ranking measure, which takes redundancies of features into account, allows us to analyze the importance of features and reduce them effectively. While some visual features like color saturation and hue showed to be important, some NIR scores could even be dropped. Finally, we generalize this approach to analyze raw NIR-spectra instead of score values and apply it to plastic waste sorting.
    9 schema:editor N53d3bcaf78c44c698e25ffa266e624ad
    10 schema:genre chapter
    11 schema:inLanguage en
    12 schema:isAccessibleForFree false
    13 schema:isPartOf N97b77267520b451c8bc1b1e4c2dc3523
    14 schema:name Generic Paper and Plastic Recognition by Fusion of NIR and VIS Data and Redundancy-Aware Feature Ranking
    15 schema:pagination 30-45
    16 schema:productId N0246b04c7bd3452e82f7b0a5341252f2
    17 N1fa696ffac254500bea7643a5b620eb6
    18 Ndf801e978d3d4e309994283bfa84ad3c
    19 schema:publisher Ne551750db0a3418fb0611eed345ff542
    20 schema:sameAs https://app.dimensions.ai/details/publication/pub.1107688601
    21 https://doi.org/10.1007/978-3-030-02686-8_3
    22 schema:sdDatePublished 2019-04-16T04:39
    23 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    24 schema:sdPublisher Nbd3715dbec434e30912b70d47603348f
    25 schema:url https://link.springer.com/10.1007%2F978-3-030-02686-8_3
    26 sgo:license sg:explorer/license/
    27 sgo:sdDataset chapters
    28 rdf:type schema:Chapter
    29 N0246b04c7bd3452e82f7b0a5341252f2 schema:name dimensions_id
    30 schema:value pub.1107688601
    31 rdf:type schema:PropertyValue
    32 N03b50c843fef4c38abb98222a1fc9705 rdf:first Nc184e2cbb46542ffa36e20f56fd206dc
    33 rdf:rest Na73f4da259d4406cb6a789bf78d6e771
    34 N0fc5d5f90ede43949ed6c27b6d6d3e3d schema:affiliation https://www.grid.ac/institutes/grid.434949.7
    35 schema:familyName Serebryanyk
    36 schema:givenName Alla
    37 rdf:type schema:Person
    38 N1fa696ffac254500bea7643a5b620eb6 schema:name doi
    39 schema:value 10.1007/978-3-030-02686-8_3
    40 rdf:type schema:PropertyValue
    41 N53d3bcaf78c44c698e25ffa266e624ad rdf:first Nc343ef72d1684d609a25b1c150f05f0e
    42 rdf:rest N03b50c843fef4c38abb98222a1fc9705
    43 N6304ce1b76e84a46afdaa728a73ab602 rdf:first sg:person.011344614151.63
    44 rdf:rest Nb8cea29b1ce34da3b46303c8e88e54a8
    45 N73cf1de4928c40768d644b8ad0c73538 rdf:first N0fc5d5f90ede43949ed6c27b6d6d3e3d
    46 rdf:rest N6304ce1b76e84a46afdaa728a73ab602
    47 N97b77267520b451c8bc1b1e4c2dc3523 schema:isbn 978-3-030-02685-1
    48 978-3-030-02686-8
    49 schema:name Proceedings of the Future Technologies Conference (FTC) 2018
    50 rdf:type schema:Book
    51 Na73f4da259d4406cb6a789bf78d6e771 rdf:first Ne9ce7de066e3451a8693b37af0128664
    52 rdf:rest rdf:nil
    53 Nb8cea29b1ce34da3b46303c8e88e54a8 rdf:first sg:person.011773470723.11
    54 rdf:rest rdf:nil
    55 Nbd3715dbec434e30912b70d47603348f schema:name Springer Nature - SN SciGraph project
    56 rdf:type schema:Organization
    57 Nc184e2cbb46542ffa36e20f56fd206dc schema:familyName Bhatia
    58 schema:givenName Rahul
    59 rdf:type schema:Person
    60 Nc343ef72d1684d609a25b1c150f05f0e schema:familyName Arai
    61 schema:givenName Kohei
    62 rdf:type schema:Person
    63 Ndf801e978d3d4e309994283bfa84ad3c schema:name readcube_id
    64 schema:value 1b8845a8d92ed21b34f87911d0e61ce96eb1cecd03c8879cf52a94eac317bd43
    65 rdf:type schema:PropertyValue
    66 Ne551750db0a3418fb0611eed345ff542 schema:location Cham
    67 schema:name Springer International Publishing
    68 rdf:type schema:Organisation
    69 Ne9ce7de066e3451a8693b37af0128664 schema:familyName Kapoor
    70 schema:givenName Supriya
    71 rdf:type schema:Person
    72 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    73 schema:name Information and Computing Sciences
    74 rdf:type schema:DefinedTerm
    75 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    76 schema:name Artificial Intelligence and Image Processing
    77 rdf:type schema:DefinedTerm
    78 sg:person.011344614151.63 schema:affiliation https://www.grid.ac/institutes/grid.7700.0
    79 schema:familyName Zisler
    80 schema:givenName Matthias
    81 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011344614151.63
    82 rdf:type schema:Person
    83 sg:person.011773470723.11 schema:affiliation https://www.grid.ac/institutes/grid.434949.7
    84 schema:familyName Schnörr
    85 schema:givenName Claudius
    86 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011773470723.11
    87 rdf:type schema:Person
    88 sg:pub.10.1007/s13762-013-0222-3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1032595097
    89 https://doi.org/10.1007/s13762-013-0222-3
    90 rdf:type schema:CreativeWork
    91 https://doi.org/10.1016/j.patrec.2010.03.014 schema:sameAs https://app.dimensions.ai/details/publication/pub.1021405554
    92 rdf:type schema:CreativeWork
    93 https://www.grid.ac/institutes/grid.434949.7 schema:alternateName Munich University of Applied Sciences
    94 schema:name University of Applied Sciences Munich, Munich, Germany
    95 rdf:type schema:Organization
    96 https://www.grid.ac/institutes/grid.7700.0 schema:alternateName Heidelberg University
    97 schema:name Institute of Applied Mathematics, University of Heidelberg, Heidelberg, Germany
    98 rdf:type schema:Organization
     




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


    ...