This paper describes new capabilities of ImageRefiner, an automatic image enhancement system based on machine learning (ML). ImageRefiner was initially designed as a pre-OCR cleanup filter for bitonal (black-and-white) document images. Using a single neural network, ImageRefiner learned which image enhancement transformations (filters) were best suited for a given document image and a given OCR engine, based on various image measurements (characteristics). The new release improves ImageRefiner in three major ways. First, to process grayscale document images, we have included three grayscale filters based on smart thresholding and noise filtering, as well as five image characteristics that are all byproducts of various thresholding techniques. Second, we have implemented additional ML algorithms, including a neural network ensemble and several "all-pairs" classifiers. Third, we have introduced a measure that evaluates overall performance of the system in terms of cumulative improvement of OCR accuracy. Our experiments indicate that OCR accuracy on enhanced grayscale images is higher than that of both the original grayscale images and the corresponding bitonal images obtained by scanning the same documents. We have noticed that the system's performance may suffer when document characteristics are correlated.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Adaptive pre-OCR cleanup of grayscale document images


    Beteiligte:
    Zavorin, Ilya (Autor:in) / Borovikov, Eugene (Autor:in) / Turner, Mark (Autor:in) / Hernandez, Luis (Autor:in)

    Kongress:

    Document Recognition and Retrieval XIII ; 2006 ; San Jose,California,United States


    Erschienen in:

    Erscheinungsdatum :

    2006-01-15





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Document image cleanup and binarization

    Wu, Victor / Manmatha, Raghaven | SPIE | 1998


    Fully automatic coloring of grayscale images

    Vieira, L. F. / Nascimento, E. R. / Fernandes, F. A. et al. | British Library Online Contents | 2007


    A Method for Two-Dimensional Adaptive Filtering of Grayscale Markov-Type Images

    Trubin, I. S. / Petrov, E. P. / Butorin, E. L. | British Library Online Contents | 2005


    Morphological compression of grayscale images of text

    Pyt’ev, Y. P. / Falomkin, I. I. / Chulichkov, A. I. | British Library Online Contents | 2006


    Extraction of Shape Skeletons from Grayscale Images

    Sibel Goktepe Tari, Z. / Shah, J. / Pien, H. | British Library Online Contents | 1997