Handwritten text line segmentation using Fully Convolutional Network

被引：34

作者：

Renton, Guillaume ^{[1
]}

Chatelain, Clement ^{[1
]}

Adam, Sebastien ^{[1
]}

Kermorvant, Christopher ^{[1
,2
]}

Paquet, Thierry ^{[1
]}

机构：

[1] Normandie Univ, UNIROUEN, UNIHAVRE, INSA Rouen,LITIS, F-76000 Rouen, France

[2] TEKLIA SAS, Paris, France

来源：

2017 14TH IAPR INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR 2017), VOL 5 | 2017年

关键词：

Fully Convolutional Networks; line segmentation; Dilated Convolutions; Document Layout Analysis;

D O I：

10.1109/ICDAR.2017.321

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we propose a learning based method for handwritten text line segmentation in document images. The originality of our approach rely on i) the use of X-height labeling of the textline, which provides a suitable text line representation for text recognition, and ii) a variant of deep Fully Convolutional Network (FCN) based on dilated convolutions. Results are given on a public dataset and compare favorably to a standard handmade segmentation approach.

引用

页码：5 / 9

页数：5

共 50 条

[1] Text line segmentation using a fully convolutional network in handwritten document images
Quang Nhat Vo
Kim, Soo Hyung
Yang, Hyung Jeong
Lee, Guee Sang
[J]. IET IMAGE PROCESSING, 2018, 12 (03) : 438 - 446
[2] Fully convolutional network with dilated convolutions for handwritten text line segmentation
Guillaume Renton
Yann Soullard
Clément Chatelain
Sébastien Adam
Christopher Kermorvant
Thierry Paquet
[J]. International Journal on Document Analysis and Recognition (IJDAR), 2018, 21 : 177 - 186
[3] Fully convolutional network with dilated convolutions for handwritten text line segmentation
Renton, Guillaume
Soullard, Yann
Chatelain, Clement
Adam, Sebastien
Kermorvant, Christopher
Paquet, Thierry
[J]. INTERNATIONAL JOURNAL ON DOCUMENT ANALYSIS AND RECOGNITION, 2018, 21 (03) : 177 - 186
[4] Text Line Segmentation for Challenging Handwritten Document Images Using Fully Convolutional Network
Barakat, Berat
Droby, Ahmad
Kassis, Majeed
El-Sana, Jihad
[J]. PROCEEDINGS 2018 16TH INTERNATIONAL CONFERENCE ON FRONTIERS IN HANDWRITING RECOGNITION (ICFHR), 2018, : 374 - 379
[5] Fully Convolutional Recurrent Network for Handwritten Chinese Text Recognition
Xie, Zecheng
Sun, Zenghui
Jin, Lianwen
Feng, Ziyong
Zhang, Shuye
[J]. 2016 23RD INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2016, : 4011 - 4016
[6] Recurrence-free unconstrained handwritten text recognition using gated fully convolutional network
Coquenet, Denis
Chatelain, Clement
Paquet, Thierry
[J]. 2020 17TH INTERNATIONAL CONFERENCE ON FRONTIERS IN HANDWRITING RECOGNITION (ICFHR 2020), 2020, : 19 - 24
[7] Page Segmentation for Historical Handwritten Documents Using Fully Convolutional Networks
Xu, Yue
He, Wenhao
Yin, Fei
Liu, Cheng-Lin
[J]. 2017 14TH IAPR INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR), VOL 1, 2017, : 541 - 546
[8] Text line segmentation in handwritten document using a production system
Nicolas, S
Paquet, T
Heutte, L
[J]. NINTH INTERNATIONAL WORKSHOP ON FRONTIERS IN HANDWRITING RECOGNITION, PROCEEDINGS, 2004, : 245 - 250
[9] LINE SEGMENTATION OF HANDWRITTEN TEXT USING HISTOGRAMS AND TENSOR VOTING
Babczynski, Tomasz
Ptak, Roman
[J]. INTERNATIONAL JOURNAL OF APPLIED MATHEMATICS AND COMPUTER SCIENCE, 2020, 30 (03) : 585 - 596
[10] Influence of Text Line Segmentation in Handwritten Text Recognition
Romero, Veronica
Andreu Sanchez, Joan
Bosch, Vicente
Depuydt, Katrien
de Does, Jesse
[J]. 2015 13TH IAPR INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR), 2015, : 536 - 540

← 1 2 3 4 5 →