JokerGAN: Memory-Efficient Model for Handwritten Text Generation with Text Line Awareness
Jan Zdenek, Hideki Nakayama
2021Year
22Citations
Abstract
Collecting labeled data for training of models for image recognition problems, including handwritten text recognition (HTR), is a tedious and expensive task. Recent work on handwritten text generation shows that generative models can be used as a data augmentation method to improve the performance of HTR systems.
Ask about this paper
Ask your agent about it.
Lune has read the top-tier papers around this one, so every answer names the papers it rests on.
Related papers
- ScrabbleGAN: Semi-Supervised Varying Length Handwritten Text GenerationSharon Fogel, Hadar Averbuch-Elor, Sarel Cohen, Shai Mazor et al.CVPR 2020
- Learn to Augment: Joint Data Augmentation and Network Optimization for Text RecognitionCanjie Luo, Yuanzhi Zhu, Lianwen Jin, Yongpan WangCVPR 2020
- Automatic Transcription of Handwritten Old Occitan LanguageEsteban Garces Arias, Vallari Pai, Matthias Schöffel, Christian Heumann et al.EMNLP 2023 · 2 citations
- Conditional Text Image Generation with Diffusion ModelsYuanzhi Zhu, Zhaohai Li, Tianwei Wang, Mengchao He et al.CVPR 2023
- What if We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer LabelsJeonghun Baek, Yusuke Matsui, Kiyoharu AizawaCVPR 2021
