We describe a new approach for evaluating page segmentation algorithms. Unlike techniques that rely on OCR output, our method is region-based: the segmentation output, described as a set of regions together with their types, output order etc., is matched against the pre-stored set of ground-truth regions. Misclassifications, splitting, and merging of regions are among the errors that are detected by the system. Each error is weighted individually for a particular application and a global estimate of segmentation quality is derived. The system can be customized to benchmark specific aspects of segmentation (e.g., headline detection) and according to the type of error correction that might follow (e.g., re-typing). Segmentation ground-truth files are quickly and easily generated and edited using GroundsKeeper, an X-Window based tool that allows one to view a document, manually draw regions (arbitrary polygons) on it, and specify information about each region (e.g., type, parent).


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Ground-truthing and benchmarking document page segmentation


    Contributors:


    Publication date :

    1995-01-01


    Size :

    500540 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Ground-Truthing and Benchmarking Document Page Segmentation

    Yanikoglu, B. A. / Vincent, L. | British Library Conference Proceedings | 1995


    Evaluating SEE: a benchmarking system for document page segmentation

    Agne, S. / Dengel, A. / Klein, B. | IEEE | 2003


    Evaluating SEE - A Benchmarking System for Document Page Segmentation

    Agne, S. / Dengel, A. / Klein, B. et al. | British Library Conference Proceedings | 2003


    Workshop—Ground Truthing and Virtual Field Trips

    Dawkins, O / Young, GW | BASE | 2020

    Free access

    Benchmarking page segmentation algorithms

    Randriamasy / Vincent | IEEE | 1994