Chinese Text Recognition
Chinese text recognition (CTR) aims to automatically convert images of Chinese text into machine-readable form, addressing challenges posed by the complexity of Chinese characters and diverse writing styles. Current research focuses on improving accuracy and robustness using deep learning models, particularly convolutional neural networks (CNNs) and transformers, often incorporating techniques like attention mechanisms, pre-training with large language models (LLMs), and multi-modal fusion. Advances in CTR have significant implications for various applications, including document processing, autonomous driving, and accessibility technologies, while also driving innovation in domain generalization and weakly supervised learning methods.
Papers
PageNet: Towards End-to-End Weakly Supervised Page-Level Handwritten Chinese Text Recognition
Dezhi Peng, Lianwen Jin, Yuliang Liu, Canjie Luo, Songxuan Lai
Recognition of Handwritten Chinese Text by Segmentation: A Segment-annotation-free Approach
Dezhi Peng, Lianwen Jin, Weihong Ma, Canyu Xie, Hesuo Zhang, Shenggao Zhu, Jing Li