About: Improved Two-Step Binarization of Degraded Document Images Based on Gaussian Mixture Model

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: Improved Two-Step Binarization of Degraded Document Images Based on Gaussian Mixture Model Goto Sponge NotDistinct Permalink

An Entity of Type : schema:ScholarlyArticle, within Data Space : covidontheweb.inria.fr associated with source document(s)

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
has title	Improved Two-Step Binarization of Degraded Document Images Based on Gaussian Mixture Model
Creator	Krupiński, Robert Lech, Piotr Okarma, Krzysztof
Source	PMC
abstract	Image binarization is one of the most relevant preprocessing operations influencing the results of further image analysis conducted for many purposes. During this step a significant loss of information occurs and the use of inappropriate thresholding methods may cause difficulties in further shape analysis or even make it impossible to recognize different shapes of objects or characters. Some of the most typical applications utilizing the analysis of binary images are Optical Character Recognition (OCR) and Optical Mark Recognition (OMR), which may also be applied for unevenly illuminated natural images, as well as for challenging degraded historical document images, considered as typical benchmarking tools for image binarization algorithms. To face the still valid challenge of relatively fast and simple, but robust binarization of degraded document images, a novel two-step algorithm utilizing initial thresholding, based on the modelling of the simplified image histogram using Gaussian Mixture Model (GMM) and the Monte Carlo method, is proposed in the paper. This approach can be considered as the extension of recently developed image preprocessing method utilizing Generalized Gaussian Distribution (GGD), based on the assumption of its similarity to the histograms of ground truth binary images distorted by Gaussian noise. The processing time of the first step, producing the intermediate images with partially removed background information, may be significantly reduced due to the use of the Monte Carlo method. The proposed improved approach leads to even better results, not only for well-known DIBCO benchmarking databases, but also for more demanding Bickley Diary dataset, allowing the use of some well-known classical binarization methods, including the global ones, in the second step of the algorithm.
has issue date	2020-05-25(xsd:dateTime)
bibo:doi	10.1007/978-3-030-50426-7_35
has license	no-cc
sha1sum (hex)	b63a618031dcf86e0093ae86ce25e2e59ab958ed
schema:url	https://doi.org/10.1007/978-3-030-50426-7_35
resource representing a document's title	Improved Two-Step Binarization of Degraded Document Images Based on Gaussian Mixture Model
has PubMed Central identifier	PMC7302549
schema:publication	Computational Science - ICCS 2020
resource representing a document's body	covid:b63a618031dcf86e0093ae86ce25e2e59ab958ed#body_text
is schema:about of	named entity 'historical document' named entity 'Images' named entity 'Two-Step' named entity 'applications' named entity 'benchmarking tools' named entity 'shape analysis' named entity 'images' named entity 'OMR' named entity 'influencing' named entity 'Some' named entity 'image' named entity 'preprocessing' named entity 'binary images' named entity 'Optical Character Recognition' named entity 'shape analysis' named entity 'OMR' named entity 'benchmarking tools' named entity 'Optical Mark Recognition' named entity 'Binarization' named entity 'Gaussian Mixture Model' named entity 'point spread function' named entity 'PSNR' named entity 'greyscale' named entity 'photocopying' named entity 'binarization' named entity 'Otsu' named entity 'input data' named entity 'pixel' named entity 'histograms' named entity 'probability distributions' named entity 'histograms' named entity 'Gaussian distribution' named entity 'GMM' named entity 'standard deviation' named entity 'Gaussian Distribution' named entity 'OCR' named entity 'PSNR' named entity 'histogram' named entity 'PSNR' named entity 'algorithm' named entity 'PSNR' named entity 'thresholding' named entity 'weighted average' named entity 'thresholding' named entity 'weighted average' named entity 'Gaussian distribution' named entity 'Laplacian distribution' named entity 'binarization' named entity 'binarization' named entity 'image processing' named entity 'binary images' named entity 'PSNR' named entity 'PSNR' named entity 'weighted average' named entity 'histogram' named entity 'photocopies' named entity 'binarization' named entity 'computational burden' named entity 'probability density function' named entity 'vector' named entity 'thresholding' named entity 'shape parameter' named entity 'maximum likelihood' named entity 'Otsu' named entity 'F-Measure' named entity 'Monte Carlo method' named entity 'histograms' named entity 'standard deviations' named entity 'histogram' named entity 'pixel' named entity 'printed documents' named entity 'Precision, Recall' named entity 'practical applications' named entity 'uniform distribution' named entity 'vector' named entity 'image quality assessment' named entity 'ICDAR' named entity 'time-consuming' named entity 'kernel' named entity 'pixel' named entity 'binary image'

Faceted Search & Find service v1.13.91 as of Mar 24 2020

Alternative Linked Data Documents: Sponger | ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3229 as of Jul 10 2020, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (94 GB total memory)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software