Unsupervised Adaptation for Synthetic-to-Real Handwritten Word Recognition

被引:0
|
作者
Kang, Lei [1 ,2 ]
Rusinol, Marcal [1 ]
Fornes, Alicia [1 ]
Riba, Pau [1 ]
Villegas, Mauricio [2 ]
机构
[1] Univ Autonoma Barcelona, Comp Vis Ctr, Barcelona, Spain
[2] Omni Us, Berlin, Germany
关键词
WRITER ADAPTATION;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Handwritten Text Recognition (HTR) is still a challenging problem because it must deal with two important difficulties: the variability among writing styles, and the scarcity of labelled data. To alleviate such problems, synthetic data generation and data augmentation are typically used to train HTR systems. However, training with such data produces encouraging but still inaccurate transcriptions in real words. In this paper, we propose an unsupervised writer adaptation approach that is able to automatically adjust a generic handwritten word recognizer, fully trained with synthetic fonts, towards a new incoming writer. We have experimentally validated our proposal using five different datasets, covering several challenges (i) the document source: modern and historic samples, which may involve paper degradation problems; (ii) different handwriting styles: single and multiple writer collections; and (iii) language, which involves different character combinations. Across these challenging collections, we show that our system is able to maintain its performance, thus, it provides a practical and generic approach to deal with new document collections without requiring any expensive and tedious manual annotation step.
引用
收藏
页码:3491 / 3500
页数:10
相关论文
共 50 条
  • [1] Self-Training of Handwritten Word Recognition for Synthetic-to-Real Adaptation
    Wolf, Fabian
    Fink, Gernot A.
    [J]. 2022 26TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2022, : 3885 - 3892
  • [2] Synthetic-to-Real Adaptation for Complex Action Recognition in Surveillance Applications
    Lu, Shuhong
    Jin, Zhangyu
    Rajendran, Vickram
    Harari, Michal
    Feng, Andrew
    De Melo, Celso M.
    [J]. SYNTHETIC DATA FOR ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING: TOOLS, TECHNIQUES, AND APPLICATIONS II, 2024, 13035
  • [3] Synthetic-to-Real Domain Adaptation for Action Recognition: A Dataset and Baseline Performances
    Reddy, Arun V.
    Shah, Ketul
    Paul, William
    Mocharla, Rohita
    Hoffman, Judy
    Katyal, Kapil D.
    Manocha, Dinesh
    de Melo, Celso M.
    Chellappa, Rama
    [J]. 2023 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2023), 2023, : 11374 - 11381
  • [4] Synthetic-to-Real Domain Adaptation for Object Instance Segmentation
    Zhang, Hui
    Tian, Yonglin
    Wang, Kunfeng
    He, Haibo
    Wang, Fei-Yue
    [J]. 2019 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2019,
  • [5] VisDA: A Synthetic-to-Real Benchmark for Visual Domain Adaptation
    Peng, Xingchao
    Usman, Ben
    Kaushik, Neela
    Wang, Dequan
    Hoffman, Judy
    Saenko, Kate
    [J]. PROCEEDINGS 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW), 2018, : 2102 - 2107
  • [6] Unsupervised writer style adaptation for handwritten word spotting
    Rodriguez, Jose A.
    Perronnin, Florent
    Sanchez, Gemma
    Llados, Josep
    [J]. 19TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOLS 1-6, 2008, : 3039 - 3042
  • [7] Content Disentanglement for Semantically Consistent Synthetic-to-Real Domain Adaptation
    Keser, Mert
    Savkin, Artem
    Tombari, Federico
    [J]. 2021 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2021, : 3844 - 3849
  • [8] Synthetic-to-Real Domain Adaptation using Contrastive Unpaired Translation
    Imbusch, Benedikt T.
    Schwarz, Max
    Behnke, Sven
    [J]. 2022 IEEE 18TH INTERNATIONAL CONFERENCE ON AUTOMATION SCIENCE AND ENGINEERING (CASE), 2022, : 595 - 602
  • [9] Unsupervised writer adaptation applied to handwritten text recognition
    Nosary, A
    Heutte, L
    Paquet, T
    [J]. PATTERN RECOGNITION, 2004, 37 (02) : 385 - 388
  • [10] N-ROD: a Neuromorphic Dataset for Synthetic-to-Real Domain Adaptation
    Cannici, Marco
    Plizzari, Chiara
    Planamente, Mirco
    Ciccone, Marco
    Bottino, Andrea
    Caputo, Barbara
    Matteucci, Matteo
    [J]. 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2021, 2021, : 1342 - 1347