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document segmentation; historical document processing; document layout analysis; neural network; deep learning;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 We argue that the diversity of historical document processing tasks prohibits to solve them one at a time and shows a need for designing generic approaches in order to handle the variability of historical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
  • [31] The use of deep-learning based CBCT segmentation in adaptive radiotherapy
    Yang, X.
    Lei, Y.
    Roper, J.
    Patel, P.
    Jani, A.
    Bradley, J.
    Liu, T.
    RADIOTHERAPY AND ONCOLOGY, 2021, 161 : S364 - S365
  • [32] Deep-learning approach to the structure of amorphous silicon
    Comin, Massimiliano
    Lewis, Laurent J.
    PHYSICAL REVIEW B, 2019, 100 (09)
  • [33] A Deep-Learning Approach to Driver Drowsiness Detection
    Ahmed, Mohammed Imran Basheer
    Alabdulkarem, Halah
    Alomair, Fatimah
    Aldossary, Dana
    Alahmari, Manar
    Alhumaidan, Munira
    Alrassan, Shoog
    Rahman, Atta
    Youldash, Mustafa
    Zaman, Gohar
    SAFETY, 2023, 9 (03)
  • [34] A Generic Cryptographic Deep-Learning Inference Platform for Remote Sensing Scenes
    Chen, Qian
    Wu, Yulin
    Wang, Xuan
    Jiang, Zoe L.
    Zhang, Weizhe
    Liu, Yang
    Alazab, Mamoun
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2023, 16 : 3309 - 3321
  • [35] Deep-Learning Segmentation of Urinary Stones in Noncontrast Computed Tomography
    Kim, Young In
    Song, Sang Hoon
    Park, Juhyun
    Youn, Hye Jung
    Kweon, Jihoon
    Park, Hyung Keun
    JOURNAL OF ENDOUROLOGY, 2023, 37 (05) : 595 - 606
  • [36] Deep-Learning Based Cell Segmentation and Deconvolution in Spatial Transcriptomics
    Kamel, Mena
    Sarangi, Amrut
    Qin, Cindy
    Barot, Het
    Senin, Pavel
    Villordo, Sergio
    Mathew, Sunaal
    Planas, Albert Pla
    Bar-Joseph, Ziv
    14TH ACM CONFERENCE ON BIOINFORMATICS, COMPUTATIONAL BIOLOGY, AND HEALTH INFORMATICS, BCB 2023, 2023,
  • [37] Breast tissue segmentation in MR images using deep-learning
    Forghani, Y.
    Timotoe, R.
    Figueiredo, M.
    Marques, T.
    Batista, E.
    Cordoso, F.
    Cardoso, M. J.
    Santinha, J.
    Gouveia, P.
    EUROPEAN JOURNAL OF CANCER, 2024, 200 : 116 - 116
  • [38] Non-segmentation and Deep-Learning Frameworks for Iris Recognition
    Wu, Wenqiang
    Chen, Ying
    Zeng, Zhuang
    BIOMETRIC RECOGNITION (CCBR 2021), 2021, 12878 : 325 - 334
  • [39] Deep-learning based segmentation of ultrasound adipose image for liposuction
    Cai, Ruxin
    Liu, Yanzhen
    Sun, Zhibin
    Wang, Yuneng
    Wang, Yu
    Li, Facheng
    Jiang, Haiyue
    INTERNATIONAL JOURNAL OF MEDICAL ROBOTICS AND COMPUTER ASSISTED SURGERY, 2023, 19 (06):
  • [40] Ensuring a connected structure for Retinal Vessels Deep-Learning Segmentation
    Dulau, Idris
    Helmer, Catherine
    Delcourt, Cecile
    Beurton-Aimar, Marie
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS, ICCVW, 2023, : 2356 - 2365