An improved approach for automatic denoising and binarization of degraded document images based on region localization

Garima Chutani; Tushar Patnaik; Vimal Dwivedi

doi:10.1109/icacci.2015.7275956

An improved approach for automatic denoising and binarization of degraded document images based on region localization

Garima Chutani, Tushar Patnaik, Vimal Dwivedi

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

6 Citations (Scopus)

Abstract

This paper presents a new binarization approach in which the binarization algorithm is neither applied on whole image as in case of global thresholding nor on sub images as in case of local thresholding. In this approach, using the concept of bounding box and edge detection method, region localization is done and the objects of interest i.e. the textual part is separated from the background part of the image. After the extraction of object of interest, local binarization is applied to only that region using the overlapping windows. The result of this approach is then compared with the result of other local binarization algorithms like midgrey, sauvola, niblack, mean etc. In this experiments were done on different datasets including DIBCO2009, DIBCO2010, DIBCO2011, DIBCO2012 and DIBCO2013. Basic evaluation parameters used for comparison are precision, recall, F-measure, mean square error (MSE), signal to noise ratio (SNR) and peak signal to noise ratio (PSNR).

Original language	English
Title of host publication	2015 International Conference on Advances in Computing, Communications and Informatics (ICACCI)
Pages	2272-2278
Number of pages	6
DOIs	https://doi.org/10.1109/icacci.2015.7275956
Publication status	Published (in print/issue) - 28 Sept 2015

Keywords

Document image binarization;
Binarization evaluation
Thresholding Technique

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/icacci.2015.7275956

Cite this

@inbook{1f1c013294e14cb99c9fbcefd4554ec2,

title = "An improved approach for automatic denoising and binarization of degraded document images based on region localization",

abstract = "This paper presents a new binarization approach in which the binarization algorithm is neither applied on whole image as in case of global thresholding nor on sub images as in case of local thresholding. In this approach, using the concept of bounding box and edge detection method, region localization is done and the objects of interest i.e. the textual part is separated from the background part of the image. After the extraction of object of interest, local binarization is applied to only that region using the overlapping windows. The result of this approach is then compared with the result of other local binarization algorithms like midgrey, sauvola, niblack, mean etc. In this experiments were done on different datasets including DIBCO2009, DIBCO2010, DIBCO2011, DIBCO2012 and DIBCO2013. Basic evaluation parameters used for comparison are precision, recall, F-measure, mean square error (MSE), signal to noise ratio (SNR) and peak signal to noise ratio (PSNR).",

keywords = "Document image binarization;, Binarization evaluation, Thresholding Technique",

author = "Garima Chutani and Tushar Patnaik and Vimal Dwivedi",

year = "2015",

month = sep,

day = "28",

doi = "10.1109/icacci.2015.7275956",

language = "English",

pages = "2272--2278",

booktitle = "2015 International Conference on Advances in Computing, Communications and Informatics (ICACCI)",

}

An improved approach for automatic denoising and binarization of degraded document images based on region localization. / Chutani, Garima; Patnaik, Tushar; Dwivedi, Vimal.
2015 International Conference on Advances in Computing, Communications and Informatics (ICACCI). 2015. p. 2272-2278.

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

TY - CHAP

T1 - An improved approach for automatic denoising and binarization of degraded document images based on region localization

AU - Chutani, Garima

AU - Patnaik, Tushar

AU - Dwivedi, Vimal

PY - 2015/9/28

Y1 - 2015/9/28

N2 - This paper presents a new binarization approach in which the binarization algorithm is neither applied on whole image as in case of global thresholding nor on sub images as in case of local thresholding. In this approach, using the concept of bounding box and edge detection method, region localization is done and the objects of interest i.e. the textual part is separated from the background part of the image. After the extraction of object of interest, local binarization is applied to only that region using the overlapping windows. The result of this approach is then compared with the result of other local binarization algorithms like midgrey, sauvola, niblack, mean etc. In this experiments were done on different datasets including DIBCO2009, DIBCO2010, DIBCO2011, DIBCO2012 and DIBCO2013. Basic evaluation parameters used for comparison are precision, recall, F-measure, mean square error (MSE), signal to noise ratio (SNR) and peak signal to noise ratio (PSNR).

AB - This paper presents a new binarization approach in which the binarization algorithm is neither applied on whole image as in case of global thresholding nor on sub images as in case of local thresholding. In this approach, using the concept of bounding box and edge detection method, region localization is done and the objects of interest i.e. the textual part is separated from the background part of the image. After the extraction of object of interest, local binarization is applied to only that region using the overlapping windows. The result of this approach is then compared with the result of other local binarization algorithms like midgrey, sauvola, niblack, mean etc. In this experiments were done on different datasets including DIBCO2009, DIBCO2010, DIBCO2011, DIBCO2012 and DIBCO2013. Basic evaluation parameters used for comparison are precision, recall, F-measure, mean square error (MSE), signal to noise ratio (SNR) and peak signal to noise ratio (PSNR).

KW - Document image binarization;

KW - Binarization evaluation

KW - Thresholding Technique

UR - http://dx.doi.org/10.1109/icacci.2015.7275956

U2 - 10.1109/icacci.2015.7275956

DO - 10.1109/icacci.2015.7275956

M3 - Chapter

SP - 2272

EP - 2278

BT - 2015 International Conference on Advances in Computing, Communications and Informatics (ICACCI)

ER -

An improved approach for automatic denoising and binarization of degraded document images based on region localization

Abstract

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this