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
  • [31] A segmentation method to handwritten word recognition
    Senouci, Mohamed
    Liazid, Abdelkrim
    Beghdadi, Hadj Ali
    Benhamamouch, Djilali
    NEURAL NETWORK WORLD, 2007, 17 (03) : 225 - 236
  • [32] ONLINE BANGLA HANDWRITTEN WORD RECOGNITION
    Bhattacharya, Nilanjana
    Roy, Partha Pratim
    Pal, Umapada
    Setua, Sanjit Kumar
    MALAYSIAN JOURNAL OF COMPUTER SCIENCE, 2018, 31 (04) : 300 - 310
  • [33] Synthetic-to-Real Domain Adaptation for Nonintrusive Load Monitoring via Reconstruction-Based Transfer Learning
    Hao, Pengfei
    Zhu, Liang
    Yan, Zhongzong
    Huang, Yingqi
    Lei, Yiwei
    Wen, He
    IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2024, 73 : 1 - 13
  • [34] Offline handwritten Amharic word recognition
    Assabie, Yaregal
    Bigun, Josef
    PATTERN RECOGNITION LETTERS, 2011, 32 (08) : 1089 - 1099
  • [35] Rejection strategies for handwritten word recognition
    Koerich, AL
    NINTH INTERNATIONAL WORKSHOP ON FRONTIERS IN HANDWRITING RECOGNITION, PROCEEDINGS, 2004, : 479 - 484
  • [36] A Study for Handwritten Devanagari Word Recognition
    Kumar, Satish
    2016 INTERNATIONAL CONFERENCE ON COMMUNICATION AND SIGNAL PROCESSING (ICCSP), VOL. 1, 2016, : 1009 - 1014
  • [37] Ensembles of classifiers for handwritten word recognition
    Simon Günter
    Horst Bunke
    Document Analysis and Recognition, 2003, 5 (4): : 224 - 232
  • [38] Offline Handwritten Gujarati Word Recognition
    Paneri, Parita R.
    Narang, Ronit
    Goswami, Mukesh M.
    2017 FOURTH INTERNATIONAL CONFERENCE ON IMAGE INFORMATION PROCESSING (ICIIP), 2017, : 188 - 192
  • [39] From Synthetic to Real: Unsupervised Domain Adaptation for Animal Pose Estimation
    Li, Chen
    Lee, Gim Hee
    2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 1482 - 1491
  • [40] Synthetic-to-real: instance segmentation of clinical cluster cells with unlabeled synthetic training
    Zhao, Meng
    Wang, Siyu
    Shi, Fan
    Jia, Chen
    Sun, Xuguo
    Chen, Shengyong
    BIOINFORMATICS, 2022, 38 (SUPPL 1) : 53 - 59