An adaptive logical method for binarization of degraded document images

  title={An adaptive logical method for binarization of degraded document images},
  author={Yibing Yang and Hong Yan},
  journal={Pattern Recognit.},
An Effective Binarization Method for Disturbed Camera-Captured Document Images
An adaptive local thresholding method which takes advantages of multi-level multi-scale local statistical information and can make the grayscale image binarization directly, without adding any postprocessing operation.
An Adaptive Layer-Based Local Binarization Technique for Degraded Documents
A new technique for adaptive binarization of degraded document images by preprocessing local background estimation stage, which detects for each pixel that is considered as background one, a proper grayscale value, to produce a new enhanced image having uniform background layers and increased local contrast.
A contrast independent algorithm for adaptive binarization of degraded document images
A contrast independent binarization algorithm that does not require any parameter setting by user that can handle various types of degraded document images and demonstrate superior performance against four well-knowbinarization algorithms.
An Adaptively Iterative Method of Document Image Binarization
An adaptively method is proposed to address the above problems and thus get expected binarization results and has been tested on the DIBCO(2009-2012) databases and gets acceptable results on most images in these databases.
Modified Sauvola binarization for degraded document images
Review of Robust Document Image BINARIZATION Technique for Degraded Document Images
The proposed method can modify algorithms and test degraded document images then compare the result that come from previous paper results, which could help to solve thresholding and filtering problem in binarization techniques.
Extraction Using Adaptive Thresholding
In this paper, a binarization technique is significantly designed for historical document images and applies a global threshold and detects image areas that are more likely to still contain noise.
Robust Document Image Binarization Technique for Degraded Document Images by using Morphological Operators
This work can modify algorithms and test degraded document images then compare the result that come from previous paper results, which will help to solve the problem of thresholding and filtering for robust document images.
Restoration of Degraded Historical Document Image: An Adaptive Multilayer-Information Binarization Technique
A new binarization method based on adaptive multilayer- information for restoration of degraded historical document images based on noise elimination, majority pixel analysis, degradation of the background layer estimation, thresholding and vicinity analysis is proposed.
A combined approach for the binarization of handwritten document images


Document Image Binarization Based on Texture Features
A texture feature based thresholding algorithm that is appreciably better than those obtained by typical existing thresholding techniques for document images with poor contrast, strong noise, complex patterns, and/or variable modalities in gray-scale histograms is developed.
Extraction of Binary Character/Graphics Images from Grayscale Document Images
This paper presents two new extraction techniques: a logical level technique and a mask-based subtraction technique, suggesting its suitability for high-speed low-cost applications.
Binarization and Multithresholding of Document Images Using Connectivity
  • L. O'Gorman
  • Computer Science
    CVGIP Graph. Model. Image Process.
  • 1994
This method has been shown to reduce the number of binarization failures from 33% to 6% on difficult images and to improve subsequent OCR recognition rates from about 95% to 97,5% on binary images.
Goal-Directed Evaluation of Binarization Methods
This paper presents a methodology for evaluation of low-level image analysis methods, using binarization (two-level thresholding) as an example, and defines the performance of the character recognition module as the objective measure.
Evaluation of Binarization Methods for Document Images
This paper presents an evaluation of eleven locally adaptive binarization methods for gray scale images with low contrast, variable background intensity and noise. Niblack's method (1986) with the
Gray Level Thresholding in Badly Illuminated Images
  • J. Parker
  • Physics
    IEEE Trans. Pattern Anal. Mach. Intell.
  • 1991
The thresholding method, called the local intensity gradient (LIG) method, was implemented in C using a Sun4 host running UNIX and properly thresholds a larger set of images than does any other method examined over the sample images tested.
Some experiments on variable thresholding
A comparative performance study of several global thresholding techniques for segmentation
Data compression for check processing machines
A comparative study shows that the proposed coding scheme performs much better than conventional predictive coding schemes and achieves a compression factor of about 8:1 for 8 gray-level image data.
Automatic multithreshold selection