Exploiting colour information for better scene text detection and recognition View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2015-06

AUTHORS

Muhammad Fraz, M. Saquib Sarfraz, Eran A. Edirisinghe

ABSTRACT

This paper presents an approach for text detection and recognition in scene images. The main contribution of this paper is to demonstrate that the colour information within the images if efficiently exploited is good enough to identify text regions from the surrounding noise. In the same way, the colour information present in character and word images can be used to achieve significant performance improvement in the recognition of characters and words. The proposed pipeline makes use of the colour information and low-level image processing operations to enhance text information that improves the overall performance of text detection and recognition in the wild. The proposed method offers two main advantages. First, it enhances the text regions up to a level of clarity where a simple off-the-shelf feature representation and classification method achieves state-of-the-art recognition performance. Second, the proposed framework is computationally fast as compared to other text detection and recognition techniques that offer good accuracy at the cost of significantly high latency. We performed extensive experimentation to evaluate our method on challenging benchmark datasets (Chars74K, ICDAR03, ICDAR11 and SVT), and the results show a considerable performance improvement. More... »

PAGES

153-167

References to SciGraph publications

  • 2011. A Method for Text Localization and Recognition in Real-World Images in COMPUTER VISION – ACCV 2010
  • 2013-09. Real-time automatic license plate recognition for CCTV forensic applications in JOURNAL OF REAL-TIME IMAGE PROCESSING
  • 2006-09. Object count/area graphs for the evaluation of object detection and segmentation algorithms in INTERNATIONAL JOURNAL ON DOCUMENT ANALYSIS AND RECOGNITION (IJDAR)
  • 2012. Large-Lexicon Attribute-Consistent Text Recognition in Natural Images in COMPUTER VISION – ECCV 2012
  • 2010. Word Spotting in the Wild in COMPUTER VISION – ECCV 2010
  • 2000-01. Automatic text segmentation and text recognition for video indexing in MULTIMEDIA SYSTEMS
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/s10032-015-0239-x

    DOI

    http://dx.doi.org/10.1007/s10032-015-0239-x

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1045716661


    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": "Loughborough University", 
              "id": "https://www.grid.ac/institutes/grid.6571.5", 
              "name": [
                "Department of Computer Science, Loughborough University, Loughborough, UK"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Fraz", 
            "givenName": "Muhammad", 
            "id": "sg:person.012336603415.92", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012336603415.92"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Karlsruhe Institute of Technology", 
              "id": "https://www.grid.ac/institutes/grid.7892.4", 
              "name": [
                "Institute of Anthoromatics and Robotics, Karlsruhe Institute of Technology, Karlsruhe, Germany"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Sarfraz", 
            "givenName": "M. Saquib", 
            "id": "sg:person.013660404353.16", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013660404353.16"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Loughborough University", 
              "id": "https://www.grid.ac/institutes/grid.6571.5", 
              "name": [
                "Department of Computer Science, Loughborough University, Loughborough, UK"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Edirisinghe", 
            "givenName": "Eran A.", 
            "id": "sg:person.012612553415.29", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012612553415.29"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "https://doi.org/10.1016/j.imavis.2005.01.004", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1001847923"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.cviu.2012.11.002", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1002413562"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1117/1.jei.22.4.041115", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1011676197"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s005300050006", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1015097688", 
              "https://doi.org/10.1007/s005300050006"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11554-011-0232-7", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1020540200", 
              "https://doi.org/10.1007/s11554-011-0232-7"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.patrec.2012.09.019", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1020939218"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/s0167-8655(03)00105-3", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1026556729"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/s0167-8655(03)00105-3", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1026556729"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-33783-3_54", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1027979069", 
              "https://doi.org/10.1007/978-3-642-33783-3_54"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-15549-9_43", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1029576618", 
              "https://doi.org/10.1007/978-3-642-15549-9_43"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-15549-9_43", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1029576618", 
              "https://doi.org/10.1007/978-3-642-15549-9_43"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-19318-7_60", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1029960837", 
              "https://doi.org/10.1007/978-3-642-19318-7_60"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-19318-7_60", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1029960837", 
              "https://doi.org/10.1007/978-3-642-19318-7_60"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/0031-3203(95)00131-x", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1035389825"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/0016-0032(80)90058-7", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1038741141"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s10032-006-0014-0", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1039213252", 
              "https://doi.org/10.1007/s10032-006-0014-0"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s10032-006-0014-0", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1039213252", 
              "https://doi.org/10.1007/s10032-006-0014-0"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/263690.263766", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1045208405"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/375360.375365", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1048171690"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/34.809116", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061157025"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/34.845381", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061157067"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tip.2008.2006661", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061641991"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tip.2011.2126586", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061642791"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2010.166", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061743884"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/965145.801294", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1063175554"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2001.990517", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093187020"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2013.157", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093261387"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iswc.2006.286368", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093263480"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iswc.2006.286368", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093263480"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/icdar.2009.97", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093296988"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/icpr.2002.1048210", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093449364"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/icpr.2004.1334351", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093467311"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2013.76", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093495720"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2013.381", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093661607"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2013.381", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093661607"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2005.177", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093997066"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/icdar.2011.144", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094000872"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2012.6247787", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094028700"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2014.516", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094071373"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/icpr.2002.1047983", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094076139"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2012.6247990", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094398830"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/icdar.2013.185", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094456801"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2013.19", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094499567"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/icdar.2011.296", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094670971"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/icdar.2013.87", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094801156"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2014.515", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094874050"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2012.6248097", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094971714"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/icdar.2011.12", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095241810"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2011.5995700", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095401204"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/icdar.2013.33", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095473692"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2010.5540041", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095483698"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2004.1315187", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095645507"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/icdar.2013.125", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095749825"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.1998.710815", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095805528"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.5244/c.26.127", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1099383164"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.5244/c.26.13", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1099383167"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.5244/c.26.63", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1099383231"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2015-06", 
        "datePublishedReg": "2015-06-01", 
        "description": "This paper presents an approach for text detection and recognition in scene images. The main contribution of this paper is to demonstrate that the colour information within the images if efficiently exploited is good enough to identify text regions from the surrounding noise. In the same way, the colour information present in character and word images can be used to achieve significant performance improvement in the recognition of characters and words. The proposed pipeline makes use of the colour information and low-level image processing operations to enhance text information that improves the overall performance of text detection and recognition in the wild. The proposed method offers two main advantages. First, it enhances the text regions up to a level of clarity where a simple off-the-shelf feature representation and classification method achieves state-of-the-art recognition performance. Second, the proposed framework is computationally fast as compared to other text detection and recognition techniques that offer good accuracy at the cost of significantly high latency. We performed extensive experimentation to evaluate our method on challenging benchmark datasets (Chars74K, ICDAR03, ICDAR11 and SVT), and the results show a considerable performance improvement.", 
        "genre": "research_article", 
        "id": "sg:pub.10.1007/s10032-015-0239-x", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": false, 
        "isPartOf": [
          {
            "id": "sg:journal.1038042", 
            "issn": [
              "1433-2833", 
              "1433-2825"
            ], 
            "name": "International Journal on Document Analysis and Recognition (IJDAR)", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "2", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "18"
          }
        ], 
        "name": "Exploiting colour information for better scene text detection and recognition", 
        "pagination": "153-167", 
        "productId": [
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "d9c4bc0e413c14fe07896f3aedc89fd9e4e5f8c800a4d959209429d3c11db6ab"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/s10032-015-0239-x"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1045716661"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1007/s10032-015-0239-x", 
          "https://app.dimensions.ai/details/publication/pub.1045716661"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2019-04-10T21:38", 
        "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_8687_00000515.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "http://link.springer.com/10.1007%2Fs10032-015-0239-x"
      }
    ]
     

    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/s10032-015-0239-x'

    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/s10032-015-0239-x'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s10032-015-0239-x'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s10032-015-0239-x'


     

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

    237 TRIPLES      21 PREDICATES      78 URIs      19 LITERALS      7 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/s10032-015-0239-x schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author N69aa45850b9446bba5f477d092ac0586
    4 schema:citation sg:pub.10.1007/978-3-642-15549-9_43
    5 sg:pub.10.1007/978-3-642-19318-7_60
    6 sg:pub.10.1007/978-3-642-33783-3_54
    7 sg:pub.10.1007/s005300050006
    8 sg:pub.10.1007/s10032-006-0014-0
    9 sg:pub.10.1007/s11554-011-0232-7
    10 https://doi.org/10.1016/0016-0032(80)90058-7
    11 https://doi.org/10.1016/0031-3203(95)00131-x
    12 https://doi.org/10.1016/j.cviu.2012.11.002
    13 https://doi.org/10.1016/j.imavis.2005.01.004
    14 https://doi.org/10.1016/j.patrec.2012.09.019
    15 https://doi.org/10.1016/s0167-8655(03)00105-3
    16 https://doi.org/10.1109/34.809116
    17 https://doi.org/10.1109/34.845381
    18 https://doi.org/10.1109/cvpr.2001.990517
    19 https://doi.org/10.1109/cvpr.2004.1315187
    20 https://doi.org/10.1109/cvpr.2005.177
    21 https://doi.org/10.1109/cvpr.2010.5540041
    22 https://doi.org/10.1109/cvpr.2011.5995700
    23 https://doi.org/10.1109/cvpr.2012.6247787
    24 https://doi.org/10.1109/cvpr.2012.6247990
    25 https://doi.org/10.1109/cvpr.2012.6248097
    26 https://doi.org/10.1109/cvpr.2013.381
    27 https://doi.org/10.1109/cvpr.2014.515
    28 https://doi.org/10.1109/cvpr.2014.516
    29 https://doi.org/10.1109/iccv.1998.710815
    30 https://doi.org/10.1109/iccv.2013.157
    31 https://doi.org/10.1109/iccv.2013.19
    32 https://doi.org/10.1109/iccv.2013.76
    33 https://doi.org/10.1109/icdar.2009.97
    34 https://doi.org/10.1109/icdar.2011.12
    35 https://doi.org/10.1109/icdar.2011.144
    36 https://doi.org/10.1109/icdar.2011.296
    37 https://doi.org/10.1109/icdar.2013.125
    38 https://doi.org/10.1109/icdar.2013.185
    39 https://doi.org/10.1109/icdar.2013.33
    40 https://doi.org/10.1109/icdar.2013.87
    41 https://doi.org/10.1109/icpr.2002.1047983
    42 https://doi.org/10.1109/icpr.2002.1048210
    43 https://doi.org/10.1109/icpr.2004.1334351
    44 https://doi.org/10.1109/iswc.2006.286368
    45 https://doi.org/10.1109/tip.2008.2006661
    46 https://doi.org/10.1109/tip.2011.2126586
    47 https://doi.org/10.1109/tpami.2010.166
    48 https://doi.org/10.1117/1.jei.22.4.041115
    49 https://doi.org/10.1145/263690.263766
    50 https://doi.org/10.1145/375360.375365
    51 https://doi.org/10.1145/965145.801294
    52 https://doi.org/10.5244/c.26.127
    53 https://doi.org/10.5244/c.26.13
    54 https://doi.org/10.5244/c.26.63
    55 schema:datePublished 2015-06
    56 schema:datePublishedReg 2015-06-01
    57 schema:description This paper presents an approach for text detection and recognition in scene images. The main contribution of this paper is to demonstrate that the colour information within the images if efficiently exploited is good enough to identify text regions from the surrounding noise. In the same way, the colour information present in character and word images can be used to achieve significant performance improvement in the recognition of characters and words. The proposed pipeline makes use of the colour information and low-level image processing operations to enhance text information that improves the overall performance of text detection and recognition in the wild. The proposed method offers two main advantages. First, it enhances the text regions up to a level of clarity where a simple off-the-shelf feature representation and classification method achieves state-of-the-art recognition performance. Second, the proposed framework is computationally fast as compared to other text detection and recognition techniques that offer good accuracy at the cost of significantly high latency. We performed extensive experimentation to evaluate our method on challenging benchmark datasets (Chars74K, ICDAR03, ICDAR11 and SVT), and the results show a considerable performance improvement.
    58 schema:genre research_article
    59 schema:inLanguage en
    60 schema:isAccessibleForFree false
    61 schema:isPartOf N1933932850c84bb286abb55731bbeee6
    62 N4b9c8ebb82594672bae25f336fcfb905
    63 sg:journal.1038042
    64 schema:name Exploiting colour information for better scene text detection and recognition
    65 schema:pagination 153-167
    66 schema:productId N2ca3eeba808f43468b1fc683bc885975
    67 N88fe1e215edf4572b39a1bc4624257a8
    68 Nf0fa9c7f147b443c98928b0d28b0f434
    69 schema:sameAs https://app.dimensions.ai/details/publication/pub.1045716661
    70 https://doi.org/10.1007/s10032-015-0239-x
    71 schema:sdDatePublished 2019-04-10T21:38
    72 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    73 schema:sdPublisher Nef3b7721aa5e49c387ea8d6ee250170b
    74 schema:url http://link.springer.com/10.1007%2Fs10032-015-0239-x
    75 sgo:license sg:explorer/license/
    76 sgo:sdDataset articles
    77 rdf:type schema:ScholarlyArticle
    78 N1933932850c84bb286abb55731bbeee6 schema:issueNumber 2
    79 rdf:type schema:PublicationIssue
    80 N2ca3eeba808f43468b1fc683bc885975 schema:name readcube_id
    81 schema:value d9c4bc0e413c14fe07896f3aedc89fd9e4e5f8c800a4d959209429d3c11db6ab
    82 rdf:type schema:PropertyValue
    83 N4b3038081ee74a18bbe5ea63897c77db rdf:first sg:person.012612553415.29
    84 rdf:rest rdf:nil
    85 N4b9c8ebb82594672bae25f336fcfb905 schema:volumeNumber 18
    86 rdf:type schema:PublicationVolume
    87 N69aa45850b9446bba5f477d092ac0586 rdf:first sg:person.012336603415.92
    88 rdf:rest Ndd0821c788f44e17a3ef3c5bc5577e62
    89 N88fe1e215edf4572b39a1bc4624257a8 schema:name doi
    90 schema:value 10.1007/s10032-015-0239-x
    91 rdf:type schema:PropertyValue
    92 Ndd0821c788f44e17a3ef3c5bc5577e62 rdf:first sg:person.013660404353.16
    93 rdf:rest N4b3038081ee74a18bbe5ea63897c77db
    94 Nef3b7721aa5e49c387ea8d6ee250170b schema:name Springer Nature - SN SciGraph project
    95 rdf:type schema:Organization
    96 Nf0fa9c7f147b443c98928b0d28b0f434 schema:name dimensions_id
    97 schema:value pub.1045716661
    98 rdf:type schema:PropertyValue
    99 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    100 schema:name Information and Computing Sciences
    101 rdf:type schema:DefinedTerm
    102 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    103 schema:name Artificial Intelligence and Image Processing
    104 rdf:type schema:DefinedTerm
    105 sg:journal.1038042 schema:issn 1433-2825
    106 1433-2833
    107 schema:name International Journal on Document Analysis and Recognition (IJDAR)
    108 rdf:type schema:Periodical
    109 sg:person.012336603415.92 schema:affiliation https://www.grid.ac/institutes/grid.6571.5
    110 schema:familyName Fraz
    111 schema:givenName Muhammad
    112 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012336603415.92
    113 rdf:type schema:Person
    114 sg:person.012612553415.29 schema:affiliation https://www.grid.ac/institutes/grid.6571.5
    115 schema:familyName Edirisinghe
    116 schema:givenName Eran A.
    117 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012612553415.29
    118 rdf:type schema:Person
    119 sg:person.013660404353.16 schema:affiliation https://www.grid.ac/institutes/grid.7892.4
    120 schema:familyName Sarfraz
    121 schema:givenName M. Saquib
    122 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013660404353.16
    123 rdf:type schema:Person
    124 sg:pub.10.1007/978-3-642-15549-9_43 schema:sameAs https://app.dimensions.ai/details/publication/pub.1029576618
    125 https://doi.org/10.1007/978-3-642-15549-9_43
    126 rdf:type schema:CreativeWork
    127 sg:pub.10.1007/978-3-642-19318-7_60 schema:sameAs https://app.dimensions.ai/details/publication/pub.1029960837
    128 https://doi.org/10.1007/978-3-642-19318-7_60
    129 rdf:type schema:CreativeWork
    130 sg:pub.10.1007/978-3-642-33783-3_54 schema:sameAs https://app.dimensions.ai/details/publication/pub.1027979069
    131 https://doi.org/10.1007/978-3-642-33783-3_54
    132 rdf:type schema:CreativeWork
    133 sg:pub.10.1007/s005300050006 schema:sameAs https://app.dimensions.ai/details/publication/pub.1015097688
    134 https://doi.org/10.1007/s005300050006
    135 rdf:type schema:CreativeWork
    136 sg:pub.10.1007/s10032-006-0014-0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1039213252
    137 https://doi.org/10.1007/s10032-006-0014-0
    138 rdf:type schema:CreativeWork
    139 sg:pub.10.1007/s11554-011-0232-7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1020540200
    140 https://doi.org/10.1007/s11554-011-0232-7
    141 rdf:type schema:CreativeWork
    142 https://doi.org/10.1016/0016-0032(80)90058-7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1038741141
    143 rdf:type schema:CreativeWork
    144 https://doi.org/10.1016/0031-3203(95)00131-x schema:sameAs https://app.dimensions.ai/details/publication/pub.1035389825
    145 rdf:type schema:CreativeWork
    146 https://doi.org/10.1016/j.cviu.2012.11.002 schema:sameAs https://app.dimensions.ai/details/publication/pub.1002413562
    147 rdf:type schema:CreativeWork
    148 https://doi.org/10.1016/j.imavis.2005.01.004 schema:sameAs https://app.dimensions.ai/details/publication/pub.1001847923
    149 rdf:type schema:CreativeWork
    150 https://doi.org/10.1016/j.patrec.2012.09.019 schema:sameAs https://app.dimensions.ai/details/publication/pub.1020939218
    151 rdf:type schema:CreativeWork
    152 https://doi.org/10.1016/s0167-8655(03)00105-3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1026556729
    153 rdf:type schema:CreativeWork
    154 https://doi.org/10.1109/34.809116 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061157025
    155 rdf:type schema:CreativeWork
    156 https://doi.org/10.1109/34.845381 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061157067
    157 rdf:type schema:CreativeWork
    158 https://doi.org/10.1109/cvpr.2001.990517 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093187020
    159 rdf:type schema:CreativeWork
    160 https://doi.org/10.1109/cvpr.2004.1315187 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095645507
    161 rdf:type schema:CreativeWork
    162 https://doi.org/10.1109/cvpr.2005.177 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093997066
    163 rdf:type schema:CreativeWork
    164 https://doi.org/10.1109/cvpr.2010.5540041 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095483698
    165 rdf:type schema:CreativeWork
    166 https://doi.org/10.1109/cvpr.2011.5995700 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095401204
    167 rdf:type schema:CreativeWork
    168 https://doi.org/10.1109/cvpr.2012.6247787 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094028700
    169 rdf:type schema:CreativeWork
    170 https://doi.org/10.1109/cvpr.2012.6247990 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094398830
    171 rdf:type schema:CreativeWork
    172 https://doi.org/10.1109/cvpr.2012.6248097 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094971714
    173 rdf:type schema:CreativeWork
    174 https://doi.org/10.1109/cvpr.2013.381 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093661607
    175 rdf:type schema:CreativeWork
    176 https://doi.org/10.1109/cvpr.2014.515 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094874050
    177 rdf:type schema:CreativeWork
    178 https://doi.org/10.1109/cvpr.2014.516 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094071373
    179 rdf:type schema:CreativeWork
    180 https://doi.org/10.1109/iccv.1998.710815 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095805528
    181 rdf:type schema:CreativeWork
    182 https://doi.org/10.1109/iccv.2013.157 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093261387
    183 rdf:type schema:CreativeWork
    184 https://doi.org/10.1109/iccv.2013.19 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094499567
    185 rdf:type schema:CreativeWork
    186 https://doi.org/10.1109/iccv.2013.76 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093495720
    187 rdf:type schema:CreativeWork
    188 https://doi.org/10.1109/icdar.2009.97 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093296988
    189 rdf:type schema:CreativeWork
    190 https://doi.org/10.1109/icdar.2011.12 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095241810
    191 rdf:type schema:CreativeWork
    192 https://doi.org/10.1109/icdar.2011.144 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094000872
    193 rdf:type schema:CreativeWork
    194 https://doi.org/10.1109/icdar.2011.296 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094670971
    195 rdf:type schema:CreativeWork
    196 https://doi.org/10.1109/icdar.2013.125 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095749825
    197 rdf:type schema:CreativeWork
    198 https://doi.org/10.1109/icdar.2013.185 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094456801
    199 rdf:type schema:CreativeWork
    200 https://doi.org/10.1109/icdar.2013.33 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095473692
    201 rdf:type schema:CreativeWork
    202 https://doi.org/10.1109/icdar.2013.87 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094801156
    203 rdf:type schema:CreativeWork
    204 https://doi.org/10.1109/icpr.2002.1047983 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094076139
    205 rdf:type schema:CreativeWork
    206 https://doi.org/10.1109/icpr.2002.1048210 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093449364
    207 rdf:type schema:CreativeWork
    208 https://doi.org/10.1109/icpr.2004.1334351 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093467311
    209 rdf:type schema:CreativeWork
    210 https://doi.org/10.1109/iswc.2006.286368 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093263480
    211 rdf:type schema:CreativeWork
    212 https://doi.org/10.1109/tip.2008.2006661 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061641991
    213 rdf:type schema:CreativeWork
    214 https://doi.org/10.1109/tip.2011.2126586 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061642791
    215 rdf:type schema:CreativeWork
    216 https://doi.org/10.1109/tpami.2010.166 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061743884
    217 rdf:type schema:CreativeWork
    218 https://doi.org/10.1117/1.jei.22.4.041115 schema:sameAs https://app.dimensions.ai/details/publication/pub.1011676197
    219 rdf:type schema:CreativeWork
    220 https://doi.org/10.1145/263690.263766 schema:sameAs https://app.dimensions.ai/details/publication/pub.1045208405
    221 rdf:type schema:CreativeWork
    222 https://doi.org/10.1145/375360.375365 schema:sameAs https://app.dimensions.ai/details/publication/pub.1048171690
    223 rdf:type schema:CreativeWork
    224 https://doi.org/10.1145/965145.801294 schema:sameAs https://app.dimensions.ai/details/publication/pub.1063175554
    225 rdf:type schema:CreativeWork
    226 https://doi.org/10.5244/c.26.127 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099383164
    227 rdf:type schema:CreativeWork
    228 https://doi.org/10.5244/c.26.13 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099383167
    229 rdf:type schema:CreativeWork
    230 https://doi.org/10.5244/c.26.63 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099383231
    231 rdf:type schema:CreativeWork
    232 https://www.grid.ac/institutes/grid.6571.5 schema:alternateName Loughborough University
    233 schema:name Department of Computer Science, Loughborough University, Loughborough, UK
    234 rdf:type schema:Organization
    235 https://www.grid.ac/institutes/grid.7892.4 schema:alternateName Karlsruhe Institute of Technology
    236 schema:name Institute of Anthoromatics and Robotics, Karlsruhe Institute of Technology, Karlsruhe, Germany
    237 rdf:type schema:Organization
     




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


    ...