Insights on the Use of Convolutional Neural Networks for Document Image Binarization

被引：0

作者：

Pastor-Pellicer, J. ^{[1
]}

Espana-Boquera, S. ^{[1
]}

Zamora-Martinez, F. ^{[2
]}

Afzal, M. Zeshan ^{[3
]}

Jose Castro-Bleda, Maria ^{[1
]}

机构：

[1] Univ Politecn Valencia, Dept Sistemas Informat & Computac, E-46022 Valencia, Spain

[2] Univ CEU Cardenal Herrera, Dept Ciencias Fis Math & Computac, Valencia, Spain

[3] German Res Ctr Artificial Intelligence DFKI, Kaiserslautern, Germany

来源：

ADVANCES IN COMPUTATIONAL INTELLIGENCE, PT II | 2015年 / 9095卷

关键词：

D O I：

10.1007/978-3-319-19222-2_10

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Convolutional Neural Networks have systematically shown good performance in Computer Vision and in Handwritten Text Recognition tasks. This paper proposes the use of these models for document image binarization. The main idea is to classify each pixel of the image into foreground and background from a sliding window centered at the pixel to be classified. An experimental analysis on the effect of sensitive parameters and some working topologies are proposed using two different corpora, of very different properties: DIBCO and Santgall.

引用

页码：115 / 126

页数：12

共 50 条

[1] Document Image Binarization with Fully Convolutional Neural Networks
Tensmeyer, Chris
Martinez, Tony
2017 14TH IAPR INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR), VOL 1, 2017, : 99 - 104
[2] Document Image Binarization Using Recurrent Neural Networks
Westphal, Florian
Lavesson, Niklas
Grahn, Hakan
2018 13TH IAPR INTERNATIONAL WORKSHOP ON DOCUMENT ANALYSIS SYSTEMS (DAS), 2018, : 263 - 268
[3] Convolutional Neural Networks for Document Image Classification
Kang, Le
Kumar, Jayant
Ye, Peng
Li, Yi
Doermann, David
2014 22ND INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2014, : 3168 - 3172
[4] Analysis of Convolutional Neural Networks for Document Image Classification
Tensmeyer, Chris
Martinez, Tony
2017 14TH IAPR INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR), VOL 1, 2017, : 388 - 393
[5] Heterogeneous Bitwidth Binarization in Convolutional Neural Networks
Fromm, Josh
Patel, Shwetak
Philipose, Matthai
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), 2018, 31
[6] Using Convolutional Encoder-Decoder for Document Image Binarization
Peng, Xujun
Cao, Huaigu
Natarajan, Prem
2017 14TH IAPR INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR), VOL 1, 2017, : 708 - 713
[7] Unsupervised neural domain adaptation for document image binarization
Castellanos, Francisco J.
Gallego, Antonio-Javier
Calvo-Zaragoza, Jorge
PATTERN RECOGNITION, 2021, 119
[8] Binarization of Degraded Document Images Using Convolutional Neural Networks and Wavelet-Based Multichannel Images
Akbari, Younes
Al-Maadeed, Somaya
Adam, Kalthoum
IEEE ACCESS, 2020, 8 (08): : 153517 - 153534
[9] DP-LinkNet: A convolutional network for historical document image binarization
Xiong, Wei
Jia, Xiuhong
Yang, Dichun
Ai, Meihui
Li, Lirong
Wang, Song
KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS, 2021, 15 (05) : 1778 - 1797
[10] Document Image Binarization Process
Prodan, Marcel
Boiangiu, Costin-Anton
BRAIN-BROAD RESEARCH IN ARTIFICIAL INTELLIGENCE AND NEUROSCIENCE, 2023, 14 (02): : 93 - 114

← 1 2 3 4 5 →