Comparison of Niblack inspired binarization methods for ancient documents

  title={Comparison of Niblack inspired binarization methods for ancient documents},
  author={Khurram Khurshid and I. Siddiqi and C. Faure and N. Vincent},
  booktitle={Electronic Imaging},
  • Khurram Khurshid, I. Siddiqi, +1 author N. Vincent
  • Published in Electronic Imaging 2009
  • Engineering, Computer Science
  • In this paper, we present a new sliding window based local thresholding technique 'NICK' and give a detailed comparison of some existing sliding-window based thresholding algorithms with our method. The proposed method aims at achieving better binarization results, specifically, for ancient document images. NICK has been inspired from the Niblack's binarization method and exhibits its robustness and effectiveness when evaluated on low quality ancient document images. 

    Topics from this paper.

    Ancient degraded document image binarization based on texture features
    • 22
    A New Adaptive Thresholding Technique for Binarizing Ancient Document
    • 4
    • Highly Influenced
    Binarization Techniques used for Grey Scale Images
    • 34
    Restoration based Contourlet Transform for historical document image binarization
    • 7
    • Highly Influenced
    Enhancement of Historical Document Images by Combining Global and Local Binarization Technique
    • 14
    • Highly Influenced
    • PDF
    A robust multi stage technique for image binarization of degraded historical documents
    • 4
    • Highly Influenced


    Publications referenced by this paper.
    Evaluation of Binarization Methods for Document Images
    • 438
    • PDF
    Adaptive document binarization
    • 226
    • Highly Influential
    • PDF
    Adaptive degraded document image binarization
    • 564
    • PDF
    A threshold selection method from gray level histograms
    • 27,976
    • PDF
    Binarising camera images for OCR
    • 73
    • PDF
    Recovery of distorted document images from bound volumes
    • 38
    • PDF
    Difficult and urgent open problems in document image analysis for libraries
    • 36
    • PDF