Performance Evaluation of Multiple Image Binarization Algorithms Using Multiple Metrics on Standard Image Databases

Sudipta Roy; Sangeet Saha; Ayan Dey; Soharab Hossain Shaikh; Nabendu Chaki

doi:10.1007/978-3-319-03095-1_38

Performance Evaluation of Multiple Image Binarization Algorithms Using Multiple Metrics on Standard Image Databases

Sudipta Roy, Sangeet Saha, Ayan Dey, Soharab Hossain Shaikh, Nabendu Chaki

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

11 Citations (Scopus)

Abstract

The area of image binarization has matured to a significant extent in last few years. There has been multiple, well-defined metrics for quantitative performance estimation of the existing techniques for binarization. However, it stills remains a problem to benchmark one binarization technique with another as different metrics are used to establish the comparative edges of different binarization approaches. In this paper, an experimental work is reported that uses three different metrics for quantitative performance evaluation of seven binarization techniques applied on four different types of images: Arial, Texture, Degraded text and MRI. Based on visually and experimentally the most appropriate methods for binarization of images have been identified for each of the four classes under consideration. We have used standard image databases along with the archived reference images, as available, for experimental purpose.

Original language	English
Title of host publication	ICT and Critical Infrastructure
Subtitle of host publication	Proceedings of the 48th Annual Convention of Computer Society of India
Editors	Suresh Chandra Satapathy, P.S. Avadhani, Siba K. Udgata, Sadasivuni Lakshminarayana
Place of Publication	Cham
Publisher	Springer, Cham
Pages	349-360
Number of pages	12
Volume	II
Edition	1
ISBN (Electronic)	9783319030951
ISBN (Print)	9783319030944
DOIs	https://doi.org/10.1007/978-3-319-03095-1_38
Publication status	Published - 1 Jan 2014
Externally published	Yes
Event	48th Annual Convention of Computer Society of India - Visakhapatnam, India Duration: 13 Dec 2013 → 15 Dec 2013 Conference number: 48

Publication series

Name	Advances in Intelligent Systems and Computing
Publisher	Springer International Publishing
Volume	249 Vol II
ISSN (Print)	2194-5357
ISSN (Electronic)	2194-5365

Conference

Conference	48th Annual Convention of Computer Society of India
Abbreviated title	CSI 2013
Country/Territory	India
City	Visakhapatnam
Period	13/12/13 → 15/12/13

Access to Document

10.1007/978-3-319-03095-1_38Licence: Unspecified

Cite this

Roy, S., Saha, S., Dey, A., Shaikh, S. H., & Chaki, N. (2014). Performance Evaluation of Multiple Image Binarization Algorithms Using Multiple Metrics on Standard Image Databases. In S. Chandra Satapathy, P. S. Avadhani, S. K. Udgata, & S. Lakshminarayana (Eds.), ICT and Critical Infrastructure: Proceedings of the 48th Annual Convention of Computer Society of India (1 ed., Vol. II, pp. 349-360). (Advances in Intelligent Systems and Computing; Vol. 249 Vol II). Springer, Cham. https://doi.org/10.1007/978-3-319-03095-1_38

Roy, Sudipta ; Saha, Sangeet ; Dey, Ayan et al. / Performance Evaluation of Multiple Image Binarization Algorithms Using Multiple Metrics on Standard Image Databases. ICT and Critical Infrastructure: Proceedings of the 48th Annual Convention of Computer Society of India. editor / Suresh Chandra Satapathy ; P.S. Avadhani ; Siba K. Udgata ; Sadasivuni Lakshminarayana. Vol. II 1. ed. Cham : Springer, Cham, 2014. pp. 349-360 (Advances in Intelligent Systems and Computing).

@inproceedings{8d92d14761f54b588d00d73303ee26a7,

title = "Performance Evaluation of Multiple Image Binarization Algorithms Using Multiple Metrics on Standard Image Databases",

abstract = "The area of image binarization has matured to a significant extent in last few years. There has been multiple, well-defined metrics for quantitative performance estimation of the existing techniques for binarization. However, it stills remains a problem to benchmark one binarization technique with another as different metrics are used to establish the comparative edges of different binarization approaches. In this paper, an experimental work is reported that uses three different metrics for quantitative performance evaluation of seven binarization techniques applied on four different types of images: Arial, Texture, Degraded text and MRI. Based on visually and experimentally the most appropriate methods for binarization of images have been identified for each of the four classes under consideration. We have used standard image databases along with the archived reference images, as available, for experimental purpose.",

keywords = "Image Thresholding, Iterative Partitioning method, Misclassification Error, Reference Image, Relative Foreground Area Error",

author = "Sudipta Roy and Sangeet Saha and Ayan Dey and Shaikh, {Soharab Hossain} and Nabendu Chaki",

year = "2014",

month = jan,

day = "1",

doi = "10.1007/978-3-319-03095-1_38",

language = "English",

isbn = "9783319030944",

volume = "II",

series = "Advances in Intelligent Systems and Computing",

publisher = "Springer, Cham",

pages = "349--360",

editor = "{Chandra Satapathy}, {Suresh } and P.S. Avadhani and Udgata, {Siba K.} and Lakshminarayana, {Sadasivuni }",

booktitle = "ICT and Critical Infrastructure",

address = "Switzerland",

edition = "1",

}

Roy, S, Saha, S, Dey, A, Shaikh, SH & Chaki, N 2014, Performance Evaluation of Multiple Image Binarization Algorithms Using Multiple Metrics on Standard Image Databases. in S Chandra Satapathy, PS Avadhani, SK Udgata & S Lakshminarayana (eds), ICT and Critical Infrastructure: Proceedings of the 48th Annual Convention of Computer Society of India. 1 edn, vol. II, Advances in Intelligent Systems and Computing, vol. 249 Vol II, Springer, Cham, Cham, pp. 349-360, 48th Annual Convention of Computer Society of India, Visakhapatnam, India, 13/12/13. https://doi.org/10.1007/978-3-319-03095-1_38

Performance Evaluation of Multiple Image Binarization Algorithms Using Multiple Metrics on Standard Image Databases. / Roy, Sudipta; Saha, Sangeet; Dey, Ayan et al.

ICT and Critical Infrastructure: Proceedings of the 48th Annual Convention of Computer Society of India. ed. / Suresh Chandra Satapathy; P.S. Avadhani; Siba K. Udgata; Sadasivuni Lakshminarayana. Vol. II 1. ed. Cham : Springer, Cham, 2014. p. 349-360 (Advances in Intelligent Systems and Computing; Vol. 249 Vol II).

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

TY - GEN

T1 - Performance Evaluation of Multiple Image Binarization Algorithms Using Multiple Metrics on Standard Image Databases

AU - Roy, Sudipta

AU - Saha, Sangeet

AU - Dey, Ayan

AU - Shaikh, Soharab Hossain

AU - Chaki, Nabendu

N1 - Conference code: 48

PY - 2014/1/1

Y1 - 2014/1/1

N2 - The area of image binarization has matured to a significant extent in last few years. There has been multiple, well-defined metrics for quantitative performance estimation of the existing techniques for binarization. However, it stills remains a problem to benchmark one binarization technique with another as different metrics are used to establish the comparative edges of different binarization approaches. In this paper, an experimental work is reported that uses three different metrics for quantitative performance evaluation of seven binarization techniques applied on four different types of images: Arial, Texture, Degraded text and MRI. Based on visually and experimentally the most appropriate methods for binarization of images have been identified for each of the four classes under consideration. We have used standard image databases along with the archived reference images, as available, for experimental purpose.

AB - The area of image binarization has matured to a significant extent in last few years. There has been multiple, well-defined metrics for quantitative performance estimation of the existing techniques for binarization. However, it stills remains a problem to benchmark one binarization technique with another as different metrics are used to establish the comparative edges of different binarization approaches. In this paper, an experimental work is reported that uses three different metrics for quantitative performance evaluation of seven binarization techniques applied on four different types of images: Arial, Texture, Degraded text and MRI. Based on visually and experimentally the most appropriate methods for binarization of images have been identified for each of the four classes under consideration. We have used standard image databases along with the archived reference images, as available, for experimental purpose.

KW - Image Thresholding

KW - Iterative Partitioning method

KW - Misclassification Error

KW - Reference Image

KW - Relative Foreground Area Error

UR - http://www.scopus.com/inward/record.url?scp=84888394569&partnerID=8YFLogxK

UR - https://link.springer.com/book/10.1007/978-3-319-03095-1

U2 - 10.1007/978-3-319-03095-1_38

DO - 10.1007/978-3-319-03095-1_38

M3 - Conference contribution

AN - SCOPUS:84888394569

SN - 9783319030944

VL - II

T3 - Advances in Intelligent Systems and Computing

SP - 349

EP - 360

BT - ICT and Critical Infrastructure

A2 - Chandra Satapathy, Suresh

A2 - Avadhani, P.S.

A2 - Udgata, Siba K.

A2 - Lakshminarayana, Sadasivuni

PB - Springer, Cham

CY - Cham

T2 - 48th Annual Convention of Computer Society of India

Y2 - 13 December 2013 through 15 December 2013

ER -

Roy S, Saha S, Dey A, Shaikh SH, Chaki N. Performance Evaluation of Multiple Image Binarization Algorithms Using Multiple Metrics on Standard Image Databases. In Chandra Satapathy S, Avadhani PS, Udgata SK, Lakshminarayana S, editors, ICT and Critical Infrastructure: Proceedings of the 48th Annual Convention of Computer Society of India. 1 ed. Vol. II. Cham: Springer, Cham. 2014. p. 349-360. (Advances in Intelligent Systems and Computing). doi: 10.1007/978-3-319-03095-1_38

Performance Evaluation of Multiple Image Binarization Algorithms Using Multiple Metrics on Standard Image Databases

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this