Deep learning for use in lumber classification tasks View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2019-03

AUTHORS

Junfeng Hu, Wenlong Song, Wei Zhang, Yafeng Zhao, Alper Yilmaz

ABSTRACT

Digital image processing has been widely used in the wood industry, and it is expected that the algorithms are accurate and have low computational complexities, especially for the real-time lumber grading and lumber classification processes. This paper investigates variations of deep learning strategies based on ResNet18 for classification of lumber images. The four datasets used in this work were manually marked as lumber defects, wood textures and lumbers by experts. A key ideal is to employ the transfer learning in the context of convolutional neural networks with a classifier layer only training with a small amount of training data for different tasks at the same lumber machinery. Through the expansion of unbalanced samples, the accuracy rate has been effectively improved. The human involvement when needed is kept to a minimum only for the training phase. The proposed approach was independently tested with four datasets, of which 80% of the data is used for training and 20% of the data is used for testing. The classification accuracy of the approach for each of the datasets is 98.16%, 93.32%, 96.64% and 99.50%. The average time for sorting the lumber image was kept at 0.003 s when the system runs on Nvidia GTX860 GPU. More... »

PAGES

505-517

References to SciGraph publications

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/s00226-019-01086-z

DOI

http://dx.doi.org/10.1007/s00226-019-01086-z

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1112389212


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": "The Ohio State University", 
          "id": "https://www.grid.ac/institutes/grid.261331.4", 
          "name": [
            "College of Mechanical and Electrical Engineering, Northeast Forestry University, 150040, Harbin, China", 
            "Department of Civil, Environmental and Geodetic Engineering, The Ohio State University, 43210, Columbus, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Hu", 
        "givenName": "Junfeng", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Northeast Forestry University", 
          "id": "https://www.grid.ac/institutes/grid.412246.7", 
          "name": [
            "College of Mechanical and Electrical Engineering, Northeast Forestry University, 150040, Harbin, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Song", 
        "givenName": "Wenlong", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Chinese Academy of Forestry", 
          "id": "https://www.grid.ac/institutes/grid.216566.0", 
          "name": [
            "Beijing Forestry Machinery Research Institute of The State Forestry Administration, 100029, Beijing, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Zhang", 
        "givenName": "Wei", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "The Ohio State University", 
          "id": "https://www.grid.ac/institutes/grid.261331.4", 
          "name": [
            "College of Mechanical and Electrical Engineering, Northeast Forestry University, 150040, Harbin, China", 
            "Department of Civil, Environmental and Geodetic Engineering, The Ohio State University, 43210, Columbus, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Zhao", 
        "givenName": "Yafeng", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "The Ohio State University", 
          "id": "https://www.grid.ac/institutes/grid.261331.4", 
          "name": [
            "Department of Civil, Environmental and Geodetic Engineering, The Ohio State University, 43210, Columbus, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Yilmaz", 
        "givenName": "Alper", 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1007/s00138-013-0526-9", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1009141472", 
          "https://doi.org/10.1007/s00138-013-0526-9"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.compag.2013.01.007", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1019873149"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00226-016-0859-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1028683224", 
          "https://doi.org/10.1007/s00226-016-0859-4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00226-016-0859-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1028683224", 
          "https://doi.org/10.1007/s00226-016-0859-4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/s0167-8655(02)00390-2", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1041018891"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00226-009-0287-9", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1045089069", 
          "https://doi.org/10.1007/s00226-009-0287-9"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00226-009-0287-9", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1045089069", 
          "https://doi.org/10.1007/s00226-009-0287-9"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00226-009-0287-9", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1045089069", 
          "https://doi.org/10.1007/s00226-009-0287-9"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1080/00207720802630685", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1049913170"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tpami.2016.2577031", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061745117"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.14257/ijsh.2015.9.5.14", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1067238945"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.14257/ijsh.2015.9.5.14", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1067238945"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.5755/j01.eie.22.6.17227", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1073102408"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2016.90", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093359587"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/3dv.2016.32", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093365817"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tsp.2012.6256397", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093422315"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icdar.2003.1227801", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094714779"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icnc.2009.594", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094809858"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2019-03", 
    "datePublishedReg": "2019-03-01", 
    "description": "Digital image processing has been widely used in the wood industry, and it is expected that the algorithms are accurate and have low computational complexities, especially for the real-time lumber grading and lumber classification processes. This paper investigates variations of deep learning strategies based on ResNet18 for classification of lumber images. The four datasets used in this work were manually marked as lumber defects, wood textures and lumbers by experts. A key ideal is to employ the transfer learning in the context of convolutional neural networks with a classifier layer only training with a small amount of training data for different tasks at the same lumber machinery. Through the expansion of unbalanced samples, the accuracy rate has been effectively improved. The human involvement when needed is kept to a minimum only for the training phase. The proposed approach was independently tested with four datasets, of which 80% of the data is used for training and 20% of the data is used for testing. The classification accuracy of the approach for each of the datasets is 98.16%, 93.32%, 96.64% and 99.50%. The average time for sorting the lumber image was kept at 0.003 s when the system runs on Nvidia GTX860 GPU.", 
    "genre": "research_article", 
    "id": "sg:pub.10.1007/s00226-019-01086-z", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isPartOf": [
      {
        "id": "sg:journal.1031697", 
        "issn": [
          "0043-7719", 
          "1432-5225"
        ], 
        "name": "Wood Science and Technology", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "2", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "53"
      }
    ], 
    "name": "Deep learning for use in lumber classification tasks", 
    "pagination": "505-517", 
    "productId": [
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "23d785bc2a8c4e371db1cb675005adc9f658d1658b1363124d6399ac28ef33d7"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/s00226-019-01086-z"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1112389212"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/s00226-019-01086-z", 
      "https://app.dimensions.ai/details/publication/pub.1112389212"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-11T12:40", 
    "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/v90/0000000363_0000000363/records_70049_00000003.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://link.springer.com/10.1007%2Fs00226-019-01086-z"
  }
]
 

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/s00226-019-01086-z'

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/s00226-019-01086-z'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s00226-019-01086-z'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s00226-019-01086-z'


 

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

136 TRIPLES      21 PREDICATES      41 URIs      19 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/s00226-019-01086-z schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N021b66f8b010472fb1e6ee3103cd995a
4 schema:citation sg:pub.10.1007/s00138-013-0526-9
5 sg:pub.10.1007/s00226-009-0287-9
6 sg:pub.10.1007/s00226-016-0859-4
7 https://doi.org/10.1016/j.compag.2013.01.007
8 https://doi.org/10.1016/s0167-8655(02)00390-2
9 https://doi.org/10.1080/00207720802630685
10 https://doi.org/10.1109/3dv.2016.32
11 https://doi.org/10.1109/cvpr.2016.90
12 https://doi.org/10.1109/icdar.2003.1227801
13 https://doi.org/10.1109/icnc.2009.594
14 https://doi.org/10.1109/tpami.2016.2577031
15 https://doi.org/10.1109/tsp.2012.6256397
16 https://doi.org/10.14257/ijsh.2015.9.5.14
17 https://doi.org/10.5755/j01.eie.22.6.17227
18 schema:datePublished 2019-03
19 schema:datePublishedReg 2019-03-01
20 schema:description Digital image processing has been widely used in the wood industry, and it is expected that the algorithms are accurate and have low computational complexities, especially for the real-time lumber grading and lumber classification processes. This paper investigates variations of deep learning strategies based on ResNet18 for classification of lumber images. The four datasets used in this work were manually marked as lumber defects, wood textures and lumbers by experts. A key ideal is to employ the transfer learning in the context of convolutional neural networks with a classifier layer only training with a small amount of training data for different tasks at the same lumber machinery. Through the expansion of unbalanced samples, the accuracy rate has been effectively improved. The human involvement when needed is kept to a minimum only for the training phase. The proposed approach was independently tested with four datasets, of which 80% of the data is used for training and 20% of the data is used for testing. The classification accuracy of the approach for each of the datasets is 98.16%, 93.32%, 96.64% and 99.50%. The average time for sorting the lumber image was kept at 0.003 s when the system runs on Nvidia GTX860 GPU.
21 schema:genre research_article
22 schema:inLanguage en
23 schema:isAccessibleForFree false
24 schema:isPartOf Nd847cc3b19eb46e38b0b1eba973eb89a
25 Nefaf97a2f65f4a0b8ff5c7abf81e259e
26 sg:journal.1031697
27 schema:name Deep learning for use in lumber classification tasks
28 schema:pagination 505-517
29 schema:productId N4e7c24ef395244b9a6ed82a09b9ba466
30 N93a763c394fa465c8d04604ce456d605
31 Nfafa427c6bba480c9d2e2c6d53589562
32 schema:sameAs https://app.dimensions.ai/details/publication/pub.1112389212
33 https://doi.org/10.1007/s00226-019-01086-z
34 schema:sdDatePublished 2019-04-11T12:40
35 schema:sdLicense https://scigraph.springernature.com/explorer/license/
36 schema:sdPublisher Nb5ae0898024c44d7903a99eab08a1a8e
37 schema:url https://link.springer.com/10.1007%2Fs00226-019-01086-z
38 sgo:license sg:explorer/license/
39 sgo:sdDataset articles
40 rdf:type schema:ScholarlyArticle
41 N021b66f8b010472fb1e6ee3103cd995a rdf:first N278b3dd1b72d4ba4a43c801d748cd533
42 rdf:rest N87ff0e0b9fcf470aa9732fb8909f9831
43 N278b3dd1b72d4ba4a43c801d748cd533 schema:affiliation https://www.grid.ac/institutes/grid.261331.4
44 schema:familyName Hu
45 schema:givenName Junfeng
46 rdf:type schema:Person
47 N27e39929ef734c98a26292e724f4927e rdf:first Ne5448fda4b6f4d398ef659adba09ca9f
48 rdf:rest rdf:nil
49 N3749bd1fce054e4ab6014d09cb7d5e54 rdf:first N6dea78cc68974069ab616e1206cfccbb
50 rdf:rest N73838c743e1d44b7b931e5d33950794f
51 N4e7c24ef395244b9a6ed82a09b9ba466 schema:name readcube_id
52 schema:value 23d785bc2a8c4e371db1cb675005adc9f658d1658b1363124d6399ac28ef33d7
53 rdf:type schema:PropertyValue
54 N6dea78cc68974069ab616e1206cfccbb schema:affiliation https://www.grid.ac/institutes/grid.216566.0
55 schema:familyName Zhang
56 schema:givenName Wei
57 rdf:type schema:Person
58 N73838c743e1d44b7b931e5d33950794f rdf:first N9d7412aabe7749218044e670ef13cc06
59 rdf:rest N27e39929ef734c98a26292e724f4927e
60 N87ff0e0b9fcf470aa9732fb8909f9831 rdf:first N960303af3d0d41acad64840d17ead1e5
61 rdf:rest N3749bd1fce054e4ab6014d09cb7d5e54
62 N93a763c394fa465c8d04604ce456d605 schema:name dimensions_id
63 schema:value pub.1112389212
64 rdf:type schema:PropertyValue
65 N960303af3d0d41acad64840d17ead1e5 schema:affiliation https://www.grid.ac/institutes/grid.412246.7
66 schema:familyName Song
67 schema:givenName Wenlong
68 rdf:type schema:Person
69 N9d7412aabe7749218044e670ef13cc06 schema:affiliation https://www.grid.ac/institutes/grid.261331.4
70 schema:familyName Zhao
71 schema:givenName Yafeng
72 rdf:type schema:Person
73 Nb5ae0898024c44d7903a99eab08a1a8e schema:name Springer Nature - SN SciGraph project
74 rdf:type schema:Organization
75 Nd847cc3b19eb46e38b0b1eba973eb89a schema:issueNumber 2
76 rdf:type schema:PublicationIssue
77 Ne5448fda4b6f4d398ef659adba09ca9f schema:affiliation https://www.grid.ac/institutes/grid.261331.4
78 schema:familyName Yilmaz
79 schema:givenName Alper
80 rdf:type schema:Person
81 Nefaf97a2f65f4a0b8ff5c7abf81e259e schema:volumeNumber 53
82 rdf:type schema:PublicationVolume
83 Nfafa427c6bba480c9d2e2c6d53589562 schema:name doi
84 schema:value 10.1007/s00226-019-01086-z
85 rdf:type schema:PropertyValue
86 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
87 schema:name Information and Computing Sciences
88 rdf:type schema:DefinedTerm
89 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
90 schema:name Artificial Intelligence and Image Processing
91 rdf:type schema:DefinedTerm
92 sg:journal.1031697 schema:issn 0043-7719
93 1432-5225
94 schema:name Wood Science and Technology
95 rdf:type schema:Periodical
96 sg:pub.10.1007/s00138-013-0526-9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1009141472
97 https://doi.org/10.1007/s00138-013-0526-9
98 rdf:type schema:CreativeWork
99 sg:pub.10.1007/s00226-009-0287-9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1045089069
100 https://doi.org/10.1007/s00226-009-0287-9
101 rdf:type schema:CreativeWork
102 sg:pub.10.1007/s00226-016-0859-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1028683224
103 https://doi.org/10.1007/s00226-016-0859-4
104 rdf:type schema:CreativeWork
105 https://doi.org/10.1016/j.compag.2013.01.007 schema:sameAs https://app.dimensions.ai/details/publication/pub.1019873149
106 rdf:type schema:CreativeWork
107 https://doi.org/10.1016/s0167-8655(02)00390-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1041018891
108 rdf:type schema:CreativeWork
109 https://doi.org/10.1080/00207720802630685 schema:sameAs https://app.dimensions.ai/details/publication/pub.1049913170
110 rdf:type schema:CreativeWork
111 https://doi.org/10.1109/3dv.2016.32 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093365817
112 rdf:type schema:CreativeWork
113 https://doi.org/10.1109/cvpr.2016.90 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093359587
114 rdf:type schema:CreativeWork
115 https://doi.org/10.1109/icdar.2003.1227801 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094714779
116 rdf:type schema:CreativeWork
117 https://doi.org/10.1109/icnc.2009.594 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094809858
118 rdf:type schema:CreativeWork
119 https://doi.org/10.1109/tpami.2016.2577031 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061745117
120 rdf:type schema:CreativeWork
121 https://doi.org/10.1109/tsp.2012.6256397 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093422315
122 rdf:type schema:CreativeWork
123 https://doi.org/10.14257/ijsh.2015.9.5.14 schema:sameAs https://app.dimensions.ai/details/publication/pub.1067238945
124 rdf:type schema:CreativeWork
125 https://doi.org/10.5755/j01.eie.22.6.17227 schema:sameAs https://app.dimensions.ai/details/publication/pub.1073102408
126 rdf:type schema:CreativeWork
127 https://www.grid.ac/institutes/grid.216566.0 schema:alternateName Chinese Academy of Forestry
128 schema:name Beijing Forestry Machinery Research Institute of The State Forestry Administration, 100029, Beijing, China
129 rdf:type schema:Organization
130 https://www.grid.ac/institutes/grid.261331.4 schema:alternateName The Ohio State University
131 schema:name College of Mechanical and Electrical Engineering, Northeast Forestry University, 150040, Harbin, China
132 Department of Civil, Environmental and Geodetic Engineering, The Ohio State University, 43210, Columbus, USA
133 rdf:type schema:Organization
134 https://www.grid.ac/institutes/grid.412246.7 schema:alternateName Northeast Forestry University
135 schema:name College of Mechanical and Electrical Engineering, Northeast Forestry University, 150040, Harbin, China
136 rdf:type schema:Organization
 




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


...