dhSegment: A generic deep-learning approach for document segmentation

被引:123
|
作者
Oliveira, Sofia Ares [1 ]
Seguin, Benoit [1 ]
Kaplan, Frederic [1 ]
机构
[1] Ecole Polytech Fed Lausanne, Digital Humanities Lab, Lausanne, VD, Switzerland
关键词
document segmentation; historical document processing; document layout analysis; neural network; deep learning;
D O I
10.1109/ICFHR-2018.2018.00011
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In recent years there have been multiple successful attempts tackling document processing problems separately by designing task specific hand-tuned strategies. We argue that the diversity of historical document processing tasks prohibits to solve them one at a time and shows a need for designing generic approaches in order to handle the variability of historical series. In this paper, we address multiple tasks simultaneously such as page extraction, baseline extraction, layout analysis or multiple typologies of illustrations and photograph extraction. We propose an open-source implementation of a CNN-based pixel-wise predictor coupled with task dependent post-processing blocks. We show that a single CNN-architecture can be used across tasks with competitive results. Moreover most of the task-specific post-precessing steps can be decomposed in a small number of simple and standard reusable operations, adding to the flexibility of our approach.
引用
收藏
页码:7 / 12
页数:6
相关论文
共 50 条
  • [21] Bellybutton: accessible and customizable deep-learning image segmentation
    Dillavou, Sam
    Hanlan, Jesse M.
    Chieco, Anthony T.
    Xiao, Hongyi
    Fulco, Sage
    Turner, Kevin T.
    Durian, Douglas J.
    SCIENTIFIC REPORTS, 2024, 14 (01):
  • [22] Classification of Photographed Document Images Based on Deep-Learning Features
    Zhong, Guoqiang
    Yao, Hui
    Liu, Yutong
    Hong, Chen
    Pham, Tuan
    EIGHTH INTERNATIONAL CONFERENCE ON GRAPHIC AND IMAGE PROCESSING (ICGIP 2016), 2017, 10225
  • [23] A New Approach to Quantify and Grade Radiation Dermatitis Using Deep-Learning Segmentation in Skin Photographs
    Park, Y. I.
    Choi, S. H.
    Hong, C. -S.
    Cho, M. -S.
    Son, J.
    Han, M. C.
    Kim, J.
    Kim, H.
    Kim, D. W.
    Kim, J. S.
    CLINICAL ONCOLOGY, 2023, 35 (01) : E10 - E19
  • [24] A panoptic segmentation dataset and deep-learning approach for explainable scoring of tumor-infiltrating lymphocytes
    Liu, Shangke
    Amgad, Mohamed
    More, Deeptej
    Rathore, Muhammad A.
    Salgado, Roberto
    Cooper, Lee A. D.
    NPJ BREAST CANCER, 2024, 10 (01)
  • [25] Validation of a Whole Heart Segmentation from Computed Tomography Imaging Using a Deep-Learning Approach
    Sam Sharobeem
    Hervé Le Breton
    Florent Lalys
    Mathieu Lederlin
    Clément Lagorce
    Marc Bedossa
    Dominique Boulmier
    Guillaume Leurent
    Pascal Haigron
    Vincent Auffret
    Journal of Cardiovascular Translational Research, 2022, 15 : 427 - 437
  • [26] A deep-learning approach for segmentation of liver tumors in magnetic resonance imaging using UNet++
    Jing Wang
    Yanyang Peng
    Shi Jing
    Lujun Han
    Tian Li
    Junpeng Luo
    BMC Cancer, 23
  • [27] Automatic hepatic tumor segmentation in intra-operative ultrasound: a supervised deep-learning approach
    Natali, Tiziano
    Zhylka, Andrey
    Olthof, Karin
    Smit, Jasper N.
    Baetens, Tarik R.
    Kok, Niels F. M.
    Kuhlmann, Koert F. D.
    Ivashchenko, Oleksandra
    Ruers, Theo J. M.
    Fusaglia, Matteo
    JOURNAL OF MEDICAL IMAGING, 2024, 11 (02)
  • [28] Validation of a Whole Heart Segmentation from Computed Tomography Imaging Using a Deep-Learning Approach
    Sharobeem, Sam
    Le Breton, Herve
    Lalys, Florent
    Lederlin, Mathieu
    Lagorce, Clement
    Bedossa, Marc
    Boulmier, Dominique
    Leurent, Guillaume
    Haigron, Pascal
    Auffret, Vincent
    JOURNAL OF CARDIOVASCULAR TRANSLATIONAL RESEARCH, 2022, 15 (02) : 427 - 437
  • [29] A deep-learning approach for segmentation of liver tumors in magnetic resonance imaging using UNet plus
    Wang, Jing
    Peng, Yanyang
    Jing, Shi
    Han, Lujun
    Li, Tian
    Luo, Junpeng
    BMC CANCER, 2023, 23 (01)
  • [30] Automated identification and segmentation of urine spots based on deep-learning
    Fan, Xin
    Li, Jun
    Yan, Junan
    PEERJ, 2024, 12