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 › Conference contribution

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)
Editors	Jaime Lloret Mauri, Sabu M. Thampi, Michal Wozniak, Oge Marques, Dilip Krishnaswamy, Sartaj Sahni, Christian Callegari, Hideyuki TAKAGI, Zoran S. Bojkovic, Vinod M, Neeli R. Prasad, Jose M. Alcaraz Calero, Joel Rodrigues, Xinyu Que, Natarajan Meghanathan, Ravi Sandhu, Edward Au
Publisher	IEEE
Pages	2272-2278
Number of pages	7
ISBN (Electronic)	9781479987924
ISBN (Print)	9781479987900
DOIs	https://doi.org/10.1109/icacci.2015.7275956
Publication status	Published - 28 Sept 2015
Externally published	Yes
Event	15th International Conference on Advances in Computing, Communications and Informatics - Kerala, India Duration: 10 Aug 2015 → 13 Aug 2015

Conference

Conference	15th International Conference on Advances in Computing, Communications and Informatics
Abbreviated title	ICACCI
Country/Territory	India
City	Kerala
Period	10/08/15 → 13/08/15

Access to Document

10.1109/icacci.2015.7275956

Cite this

Chutani, G., Patnaik, T., & Dwivedi, V. (2015). An improved approach for automatic denoising and binarization of degraded document images based on region localization. In J. Lloret Mauri, S. M. Thampi, M. Wozniak, O. Marques, D. Krishnaswamy, S. Sahni, C. Callegari, H. TAKAGI, Z. S. Bojkovic, V. M, N. R. Prasad, J. M. Alcaraz Calero, J. Rodrigues, X. Que, N. Meghanathan, R. Sandhu, & E. Au (Eds.), 2015 International Conference on Advances in Computing, Communications and Informatics (ICACCI) (pp. 2272-2278). IEEE. https://doi.org/10.1109/icacci.2015.7275956

Chutani, Garima ; Patnaik, Tushar ; Dwivedi, Vimal. / An improved approach for automatic denoising and binarization of degraded document images based on region localization. 2015 International Conference on Advances in Computing, Communications and Informatics (ICACCI). editor / Jaime Lloret Mauri ; Sabu M. Thampi ; Michal Wozniak ; Oge Marques ; Dilip Krishnaswamy ; Sartaj Sahni ; Christian Callegari ; Hideyuki TAKAGI ; Zoran S. Bojkovic ; Vinod M ; Neeli R. Prasad ; Jose M. Alcaraz Calero ; Joel Rodrigues ; Xinyu Que ; Natarajan Meghanathan ; Ravi Sandhu ; Edward Au. IEEE, 2015. pp. 2272-2278

@inproceedings{2cfaa89a642c4ded9923fc76a2bee537,

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).",

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

year = "2015",

month = sep,

day = "28",

doi = "10.1109/icacci.2015.7275956",

language = "English",

isbn = "9781479987900",

pages = "2272--2278",

editor = "{Lloret Mauri}, {Jaime } and Thampi, {Sabu M.} and Wozniak, {Michal } and Marques, {Oge } and Krishnaswamy, {Dilip } and Sahni, {Sartaj } and Christian Callegari and TAKAGI, {Hideyuki } and Bojkovic, {Zoran S. } and M, {Vinod } and Prasad, {Neeli R. } and {Alcaraz Calero}, {Jose M. } and Rodrigues, {Joel } and Que, {Xinyu } and Meghanathan, {Natarajan } and Sandhu, {Ravi } and Au, {Edward }",

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

publisher = "IEEE",

note = "15th International Conference on Advances in Computing, Communications and Informatics , ICACCI ; Conference date: 10-08-2015 Through 13-08-2015",

}

Chutani, G, Patnaik, T & Dwivedi, V 2015, An improved approach for automatic denoising and binarization of degraded document images based on region localization. in J Lloret Mauri, SM Thampi, M Wozniak, O Marques, D Krishnaswamy, S Sahni, C Callegari, H TAKAGI, ZS Bojkovic, V M, NR Prasad, JM Alcaraz Calero, J Rodrigues, X Que, N Meghanathan, R Sandhu & E Au (eds), 2015 International Conference on Advances in Computing, Communications and Informatics (ICACCI). IEEE, pp. 2272-2278, 15th International Conference on Advances in Computing, Communications and Informatics , Kerala, India, 10/08/15. https://doi.org/10.1109/icacci.2015.7275956

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). ed. / Jaime Lloret Mauri; Sabu M. Thampi; Michal Wozniak; Oge Marques; Dilip Krishnaswamy; Sartaj Sahni; Christian Callegari; Hideyuki TAKAGI; Zoran S. Bojkovic; Vinod M; Neeli R. Prasad; Jose M. Alcaraz Calero; Joel Rodrigues; Xinyu Que; Natarajan Meghanathan; Ravi Sandhu; Edward Au. IEEE, 2015. p. 2272-2278.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

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).

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

U2 - 10.1109/icacci.2015.7275956

DO - 10.1109/icacci.2015.7275956

M3 - Conference contribution

SN - 9781479987900

SP - 2272

EP - 2278

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

A2 - Lloret Mauri, Jaime

A2 - Thampi, Sabu M.

A2 - Wozniak, Michal

A2 - Marques, Oge

A2 - Krishnaswamy, Dilip

A2 - Sahni, Sartaj

A2 - Callegari, Christian

A2 - TAKAGI, Hideyuki

A2 - Bojkovic, Zoran S.

A2 - M, Vinod

A2 - Prasad, Neeli R.

A2 - Alcaraz Calero, Jose M.

A2 - Rodrigues, Joel

A2 - Que, Xinyu

A2 - Meghanathan, Natarajan

A2 - Sandhu, Ravi

A2 - Au, Edward

PB - IEEE

T2 - 15th International Conference on Advances in Computing, Communications and Informatics

Y2 - 10 August 2015 through 13 August 2015

ER -

Chutani G, Patnaik T, Dwivedi V. An improved approach for automatic denoising and binarization of degraded document images based on region localization. In Lloret Mauri J, Thampi SM, Wozniak M, Marques O, Krishnaswamy D, Sahni S, Callegari C, TAKAGI H, Bojkovic ZS, M V, Prasad NR, Alcaraz Calero JM, Rodrigues J, Que X, Meghanathan N, Sandhu R, Au E, editors, 2015 International Conference on Advances in Computing, Communications and Informatics (ICACCI). IEEE. 2015. p. 2272-2278 doi: 10.1109/icacci.2015.7275956

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

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this