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
  • [41] CraterDANet: A Convolutional Neural Network for Small-Scale Crater Detection via Synthetic-to-Real Domain Adaptation
    Yang, Huan
    Xu, Xinchao
    Ma, Youqing
    Xu, Yaming
    Liu, Shaochuang
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
  • [42] Synthetic-to-real domain adaptation with deep learning for fitting the intravoxel incoherent motion model of diffusion-weighted imaging
    Huang, Haoyuan
    Liu, Baoer
    Xu, Yikai
    Zhou, Wu
    MEDICAL PHYSICS, 2023, 50 (03) : 1614 - 1622
  • [43] Unsupervised Sim-to-Real Adaptation for Environmental Recognition in Assistive Walking
    Chen, Chuheng
    Zhang, Kuangen
    Leng, Yuquan
    Chen, Xinxing
    Fu, Chenglong
    IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, 2022, 30 : 1350 - 1360
  • [44] Robust Synthetic-to-Real Ensemble Dehazing Algorithm With the Intermediate Domain
    Qiao, Yingxu
    Wang, Xing
    Liu, Hongmin
    Huo, Zhanqiang
    IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS, 2024, 11 (04): : 5510 - 5524
  • [45] PSD: Principled Synthetic-to-Real Dehazing Guided by Physical Priors
    Chen, Zeyuan
    Wang, Yangchao
    Yang, Yang
    Liu, Dong
    2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 7176 - 7185
  • [46] Test-Time Synthetic-to-Real Adaptive Depth Estimation
    Yi, Eojindl
    Kim, Junmo
    2023 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, ICRA, 2023, : 4938 - 4944
  • [47] An offline cursive handwritten word recognition system
    Tay, YH
    Lallican, PM
    Khalid, M
    Viard-Gaudin, C
    Knerr, S
    IEEE REGION 10 INTERNATIONAL CONFERENCE ON ELECTRICAL AND ELECTRONIC TECHNOLOGY, VOLS 1 AND 2, 2001, : 519 - 524
  • [48] Unsupervised Domain Adaptation from Synthetic to Real Images for Anchorless Object Detection
    Scheck, Tobias
    Grassi, Ana Perez
    Hirtz, Gangolf
    VISAPP: PROCEEDINGS OF THE 16TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS - VOL. 5: VISAPP, 2021, : 319 - 327
  • [49] Global and Local Texture Randomization for Synthetic-to-Real Semantic Segmentation
    Peng, Duo
    Lei, Yinjie
    Liu, Lingqiao
    Zhang, Pingping
    Liu, Jun
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2021, 30 (30) : 6594 - 6608
  • [50] WORD RECOGNITION TECHNIQUES FOR KANNADA HANDWRITTEN DOCUMENTS
    Sureka, Tulika
    Swetha, K. S. N.
    Arora, Isha
    Mamatha, H. R.
    2019 10TH INTERNATIONAL CONFERENCE ON COMPUTING, COMMUNICATION AND NETWORKING TECHNOLOGIES (ICCCNT), 2019,