archive-org.com » ORG » I » IAPR-TC11.ORG

Total: 1082

Choose link from "Titles, links and description words view":

Or switch to "Titles and links view".
  • Pages that link to "ChemInfty - Chemical Structure GT" - TC11
    Help Help talk Category Category talk DAS Discussion Filters Hide transclusions Hide links Hide redirects The following pages link to ChemInfty Chemical Structure GT View previous 50 next 50 20 50 100 250 500 Chem Infty Dataset A ground truthed dataset of Chemical Structure Images links View previous 50 next 50 20 50 100 250 500 Retrieved from http www iapr tc11 org mediawiki index php Special WhatLinksHere Personal tools

    Original URL path: http://www.iapr-tc11.org/mediawiki/index.php?title=Special:WhatLinksHere&target=ChemInfty+-+Chemical+Structure+GT (2016-02-15)
    Open archived version from archive


  • Table Ground Truth for the UW3 and UNLV datasets - TC11
    OCR results file We provide these OCR result files for all the images in the dataset and each file has the same name as the basename of the image file in the original dataset We used the T Truth tool also provided below to prepare ground truth information The tool is easy to use and is described in 1 We trained a user to operate the T Truth tool and asked him to prepare the ground truth for the target images from above dataset The ground truth for each image is stored in an XML The ground truths were manually validated by another expert using the preview edit mode of the T Truth tool and improper ground truths were corrected These iterations were made several times to ensure the accuracy of the ground truth Tables in the UNLV dataset The original dataset contains 2889 pages of scanned document images from variety of sources Magazines News papers Business Letter Annual Report etc The scanned images are provided at 200 and 300 DPI resolution in bitonal grey and fax format There is ground truth data provided alongside the original dataset which contains manually marked zones zone types are provided in text format Closer examination of the dataset reveals that there are no marked table zones in the fax images so this subset is not considered here The grey images are all also present in bitonal format therefore we concentrated on bitonal documents with resolution of 300 dpi for the preparation of ground truth We selected those images for which table zones have been marked in the ground truth There are around 427 such images We provide table structure ground truths for these document images Tables in the UW 3 dataset The original dataset consists of 1600 skew corrected English document images with

    Original URL path: http://www.iapr-tc11.org/mediawiki/index.php/Table_Ground_Truth_for_the_UW3_and_UNLV_datasets (2016-02-15)
    Open archived version from archive

  • Pages that link to "Table Ground Truth for the UW3 and UNLV datasets" - TC11
    talk Help Help talk Category Category talk DAS Discussion Filters Hide transclusions Hide links Hide redirects The following pages link to Table Ground Truth for the UW3 and UNLV datasets View previous 50 next 50 20 50 100 250 500 Benchmarking of Table Structure Recognition Algorithms links Datasets per Journal Conference links Datasets List links View previous 50 next 50 20 50 100 250 500 Retrieved from http www iapr

    Original URL path: http://www.iapr-tc11.org/mediawiki/index.php?title=Special:WhatLinksHere&target=Table+Ground+Truth+for+the+UW3+and+UNLV+datasets (2016-02-15)
    Open archived version from archive

  • Benchmarking of Table Structure Recognition Algorithms - TC11
    competing algorithms need to produce the output in the XML format similar to the sample ground truth Five example output from our t recs algorithm are included in the set of samples provided for reference The output from these algorithms are then used to produce result image files which are then compared by the evaluation framework to produce following benchmarking measures Correct Detections Partial Detections Over Segmentation Under Segmentation Missed False Positives at the following levels of abstraction Table Rows Columns Cells Row spanning cells Column spanning cells Row column spanning cells The evaluation software provided below segment evaluation sh part of the T truth package expects ground truth images in the evaluation gt folder and result images in the evaluation result folder The evaluation algorithm produces a file with the extension out in the evaluation directory for each level of abstraction table row column etc with semicolon separated benchmarking measures in the following order gt img result img GroundTruthComponents SegmentationComponents Number of OverSegmentations Number of UnderSegmentations Number of FalseAlarms OverSegmentedComponents UnderSegmentedComponents False Alarms Missed Correct Partial Matches These benchmarking measures are described in 5 Related Dataset UNLV Dataset Related Ground Truth Data Table Ground Truth for the UW3 and UNLV datasets Related Software T truth Software and Samples 4 5 Mb References T Kieninger and A Dengel Applying the T RECS table recognition system to the business letter domain Proceedings of the 6th IAPR International Conference on Document Analysis and Recognition IEEE CS pp 518 522 2001 J Hu R Kashi D Lopresti and G Wilfong Medium independent table detection Proceedings of the 8th SPIE Conference on Document Recognition and Retrieval pp 291 302 2000 S Mandal S Chowdhury A Das and B Chanda A simple and effective table detection system from document images International Journal on Document Analysis

    Original URL path: http://www.iapr-tc11.org/mediawiki/index.php/Benchmarking_of_Table_Structure_Recognition_Algorithms (2016-02-15)
    Open archived version from archive

  • Pages that link to "Benchmarking of Table Structure Recognition Algorithms" - TC11
    Template talk Help Help talk Category Category talk DAS Discussion Filters Hide transclusions Hide links Hide redirects The following pages link to Benchmarking of Table Structure Recognition Algorithms View previous 50 next 50 20 50 100 250 500 Table Ground Truth for the UW3 and UNLV datasets links View previous 50 next 50 20 50 100 250 500 Retrieved from http www iapr tc11 org mediawiki index php Special WhatLinksHere

    Original URL path: http://www.iapr-tc11.org/mediawiki/index.php?title=Special:WhatLinksHere&target=Benchmarking+of+Table+Structure+Recognition+Algorithms (2016-02-15)
    Open archived version from archive

  • The DocLab Dataset for Evaluating Table Interpretation Methods - TC11
    files are in one of the following formats HTML 77 Excel 67 and CSV 20 Each file contains at least one table The dataset consists of a total of 172 tables DATASET CONSTRUCTION The files comprising the dataset were selected based on the following constraints on the tables they contained 1 Tables with rectilinear structure only 2 Tables with text in English language only 3 Tables that do not contain graphic symbols or figures 4 Non recursive tables i e no table with a table as one of its content cells 5 Non concatenated tables no tables formed by concatenating two or more tables 6 Tables which do not span more than one HTML page or Excel sheet Metadata Statistics for each table are provided in an Excel file The information recorded is table size number of rows and columns augmentations aggregates footnotes units Wang dimensionality and source Web Site Related Ground Truth Data Wang Notation for the DocLab Table Dataset Related Tasks Evaluating Web Table Interpretation Methods References Padmanabhan R Jandhyala R C Krishnamoorthy M Nagy G Seth S Silversmith W Interactive Conversion of Web Tables In Procs Eighth IAPR International Workshop on Graphics Recognition GREC 2009 City University of La Rochelle France Lecture Notes in Computer Science 6020 Springer Heidelberg In Press 2010 Seth S Jandhyala R C Krishnamoorthy M Nagy G Analysis and Taxonomy of Column Header Categories for Web Tables Oral Presentation In Procs Ninth IAPR International Workshop on Document Analysis Systems Boston Massachusetts 2010 ID 73 Nagy G Padmanabhan R Jandhyala R C Silversmith W Krishnamoorthy M Table Metadata Headers Augmentations and Aggregates In Procs Ninth IAPR International Workshop on Document Analysis Systems Boston Massachusetts 2010 ID 77 Padmanabhan R Table Abstraction Tool Master s Thesis Rensselaer Polytechnic Institute May 2009 Submitted Files Version 1

    Original URL path: http://www.iapr-tc11.org/mediawiki/index.php/The_DocLab_Dataset_for_Evaluating_Table_Interpretation_Methods (2016-02-15)
    Open archived version from archive

  • Pages that link to "The DocLab Dataset for Evaluating Table Interpretation Methods" - TC11
    Category Category talk DAS Discussion Filters Hide transclusions Hide links Hide redirects The following pages link to The DocLab Dataset for Evaluating Table Interpretation Methods View previous 50 next 50 20 50 100 250 500 Wang Notation for the DocLab Table Dataset links Evaluating Web Table Interpretation Methods links Datasets per Journal Conference links Datasets List links View previous 50 next 50 20 50 100 250 500 Retrieved from http

    Original URL path: http://www.iapr-tc11.org/mediawiki/index.php?title=Special:WhatLinksHere&target=The+DocLab+Dataset+for+Evaluating+Table+Interpretation+Methods (2016-02-15)
    Open archived version from archive

  • Wang Notation for the DocLab Table Dataset - TC11
    are also provided The ground truth information is stored an XML file Please refer to the Ground Truth Specification for the file structure of the ground truth Related Dataset The DocLab Dataset for Evaluating Table Interpretation Methods Related Tasks Evaluating Web Table Interpretation Methods Submitted Files Table Abstraction Tool 2 6MB Ground Truth Specification Augmented Wang Notation 740 KB Ground Truth Files Wang Notation of Tables 740 KB This page

    Original URL path: http://www.iapr-tc11.org/mediawiki/index.php/Wang_Notation_for_the_DocLab_Table_Dataset (2016-02-15)
    Open archived version from archive



  •