Publication

DeepOtsu: Document enhancement and binarization using iterative deep learning

He, S. & Schomaker, L., Jul-2019, In : Pattern recognition. 91, p. 379-390 12 p.

Research output: Contribution to journalArticleAcademicpeer-review

APA

He, S., & Schomaker, L. (2019). DeepOtsu: Document enhancement and binarization using iterative deep learning. Pattern recognition, 91, 379-390. https://doi.org/10.1016/j.patcog.2019.01.025

Author

He, Sheng ; Schomaker, Lambertus. / DeepOtsu : Document enhancement and binarization using iterative deep learning. In: Pattern recognition. 2019 ; Vol. 91. pp. 379-390.

Harvard

He, S & Schomaker, L 2019, 'DeepOtsu: Document enhancement and binarization using iterative deep learning', Pattern recognition, vol. 91, pp. 379-390. https://doi.org/10.1016/j.patcog.2019.01.025

Standard

DeepOtsu : Document enhancement and binarization using iterative deep learning. / He, Sheng; Schomaker, Lambertus.

In: Pattern recognition, Vol. 91, 07.2019, p. 379-390.

Research output: Contribution to journalArticleAcademicpeer-review

Vancouver

He S, Schomaker L. DeepOtsu: Document enhancement and binarization using iterative deep learning. Pattern recognition. 2019 Jul;91:379-390. https://doi.org/10.1016/j.patcog.2019.01.025


BibTeX

@article{40ae73a18dc8400ca79ade20e79dd1da,
title = "DeepOtsu: Document enhancement and binarization using iterative deep learning",
abstract = "This paper presents a novel iterative deep learning framework and applies it to document enhancement and binarization. Unlike the traditional methods that predict the binary label of each pixel on the input image, we train the neural network to learn the degradations in document images and produce uniform images of the degraded input images, which in turn allows the network to refine the output iteratively. Two different iterative methods have been studied in this paper: recurrent refinement (RR) that uses the same trained neural network in each iteration for document enhancement and stacked refinement (SR) that uses a stack of different neural networks for iterative output refinement. Given the learned nature of the uniform and enhanced image, the binarization map can be easily obtained through use of a global or local threshold. The experimental results on several public benchmark data sets show that our proposed method provides a new, clean version of the degraded image, one that is suitable for visualization and which shows promising results for binarization using Otsu's global threshold, based on enhanced images learned iteratively by the neural network. (C) 2019 Elsevier Ltd. All rights reserved.",
keywords = "IMAGE BINARIZATION, RESTORATION",
author = "Sheng He and Lambertus Schomaker",
year = "2019",
month = "7",
doi = "10.1016/j.patcog.2019.01.025",
language = "English",
volume = "91",
pages = "379--390",
journal = "Pattern recognition",
issn = "0031-3203",
publisher = "ELSEVIER SCI LTD",

}

RIS

TY - JOUR

T1 - DeepOtsu

T2 - Document enhancement and binarization using iterative deep learning

AU - He, Sheng

AU - Schomaker, Lambertus

PY - 2019/7

Y1 - 2019/7

N2 - This paper presents a novel iterative deep learning framework and applies it to document enhancement and binarization. Unlike the traditional methods that predict the binary label of each pixel on the input image, we train the neural network to learn the degradations in document images and produce uniform images of the degraded input images, which in turn allows the network to refine the output iteratively. Two different iterative methods have been studied in this paper: recurrent refinement (RR) that uses the same trained neural network in each iteration for document enhancement and stacked refinement (SR) that uses a stack of different neural networks for iterative output refinement. Given the learned nature of the uniform and enhanced image, the binarization map can be easily obtained through use of a global or local threshold. The experimental results on several public benchmark data sets show that our proposed method provides a new, clean version of the degraded image, one that is suitable for visualization and which shows promising results for binarization using Otsu's global threshold, based on enhanced images learned iteratively by the neural network. (C) 2019 Elsevier Ltd. All rights reserved.

AB - This paper presents a novel iterative deep learning framework and applies it to document enhancement and binarization. Unlike the traditional methods that predict the binary label of each pixel on the input image, we train the neural network to learn the degradations in document images and produce uniform images of the degraded input images, which in turn allows the network to refine the output iteratively. Two different iterative methods have been studied in this paper: recurrent refinement (RR) that uses the same trained neural network in each iteration for document enhancement and stacked refinement (SR) that uses a stack of different neural networks for iterative output refinement. Given the learned nature of the uniform and enhanced image, the binarization map can be easily obtained through use of a global or local threshold. The experimental results on several public benchmark data sets show that our proposed method provides a new, clean version of the degraded image, one that is suitable for visualization and which shows promising results for binarization using Otsu's global threshold, based on enhanced images learned iteratively by the neural network. (C) 2019 Elsevier Ltd. All rights reserved.

KW - IMAGE BINARIZATION

KW - RESTORATION

U2 - 10.1016/j.patcog.2019.01.025

DO - 10.1016/j.patcog.2019.01.025

M3 - Article

VL - 91

SP - 379

EP - 390

JO - Pattern recognition

JF - Pattern recognition

SN - 0031-3203

ER -

ID: 74019672