ICDAR 2019 Time-Quality Binarization Competition

Rafael Dueire Lins; Ergina Kavallieratou; Elisa Barney Smith; Rodrigo Barros Bernardino; Darlisson Marinho de Jesus

ICDAR 2019 Time-Quality Binarization Competition

Rafael Dueire Lins, Ergina Kavallieratou, Elisa Barney Smith, Rodrigo Barros Bernardino, Darlisson Marinho de Jesus

Electrical Engineering Department

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

19 Scopus citations

Abstract

The ICDAR 2019 Time-Quality Binarization Competition assessed the performance of seventeen new together with thirty previously published binarization algorithms. The quality of the resulting two-tone image and the execution time were assessed. Comparisons were on both in "real-world" and synthetic scanned images, and in documents photographed with four models of widely used portable phones. Most of the submitted algorithms employed machine learning techniques and performed best on the most complex images. Traditional algorithms provided very good results at a fraction of the time.

Original language	American English
Title of host publication	2019 International Conference on Document Analysis and Recognition (ICDAR)
State	Published - 1 Jan 2019

Keywords

algorithms
binarization
documents
historical documents
performance evaluation
quality evaluation

EGS Disciplines

Electrical and Computer Engineering

Access to Document

ICDAR 2019 Time-Quality Binarization CompetitionFinal published version, 2.55 MBLicense: Unspecified

https://dx.doi.org/10.1109/ICDAR.2019.00248

Cite this

@inbook{ced79bb468f84654a38d5e74ce59234c,

title = "ICDAR 2019 Time-Quality Binarization Competition",

abstract = " The ICDAR 2019 Time-Quality Binarization Competition assessed the performance of seventeen new together with thirty previously published binarization algorithms. The quality of the resulting two-tone image and the execution time were assessed. Comparisons were on both in {"}real-world{"} and synthetic scanned images, and in documents photographed with four models of widely used portable phones. Most of the submitted algorithms employed machine learning techniques and performed best on the most complex images. Traditional algorithms provided very good results at a fraction of the time.",

keywords = "algorithms, binarization, documents, historical documents, performance evaluation, quality evaluation",

author = "{Dueire Lins}, Rafael and Ergina Kavallieratou and {Barney Smith}, Elisa and {Barros Bernardino}, Rodrigo and {Marinho de Jesus}, Darlisson",

note = "Dueire Lins, Rafael; Kavallieratou, Ergina; Barney Smith, Elisa; Barros Bernardino, Rodrigo; and Marinho de Jesus, Darlisson. (2019). {"}ICDAR 2019 Time-Quality Binarization Competition{"}. In 2019 International Conference on Document Analysis and Recognition (ICDAR) (pp. 1539-1546). IEEE. https://doi.org/10.1109/ICDAR.2019.00248",

year = "2019",

month = jan,

day = "1",

language = "American English",

booktitle = "2019 International Conference on Document Analysis and Recognition (ICDAR)",

}

TY - CHAP

T1 - ICDAR 2019 Time-Quality Binarization Competition

AU - Dueire Lins, Rafael

AU - Kavallieratou, Ergina

AU - Barney Smith, Elisa

AU - Barros Bernardino, Rodrigo

AU - Marinho de Jesus, Darlisson

N1 - Dueire Lins, Rafael; Kavallieratou, Ergina; Barney Smith, Elisa; Barros Bernardino, Rodrigo; and Marinho de Jesus, Darlisson. (2019). "ICDAR 2019 Time-Quality Binarization Competition". In 2019 International Conference on Document Analysis and Recognition (ICDAR) (pp. 1539-1546). IEEE. https://doi.org/10.1109/ICDAR.2019.00248

PY - 2019/1/1

Y1 - 2019/1/1

N2 - The ICDAR 2019 Time-Quality Binarization Competition assessed the performance of seventeen new together with thirty previously published binarization algorithms. The quality of the resulting two-tone image and the execution time were assessed. Comparisons were on both in "real-world" and synthetic scanned images, and in documents photographed with four models of widely used portable phones. Most of the submitted algorithms employed machine learning techniques and performed best on the most complex images. Traditional algorithms provided very good results at a fraction of the time.

AB - The ICDAR 2019 Time-Quality Binarization Competition assessed the performance of seventeen new together with thirty previously published binarization algorithms. The quality of the resulting two-tone image and the execution time were assessed. Comparisons were on both in "real-world" and synthetic scanned images, and in documents photographed with four models of widely used portable phones. Most of the submitted algorithms employed machine learning techniques and performed best on the most complex images. Traditional algorithms provided very good results at a fraction of the time.

KW - algorithms

KW - binarization

KW - documents

KW - historical documents

KW - performance evaluation

KW - quality evaluation

UR - https://scholarworks.boisestate.edu/electrical_facpubs/453

M3 - Chapter

BT - 2019 International Conference on Document Analysis and Recognition (ICDAR)

ER -

ICDAR 2019 Time-Quality Binarization Competition

Abstract

Keywords

EGS Disciplines

Access to Document

Other files and links

Fingerprint

Cite this