@inproceedings{li2023trocr,
author = {Li, Minghao and Lv, Tengchao and Chen, Jingye and Cui, Lei and Lu, Yijuan and Florencio, Dinei and Zhang, Cha and Li, Zhoujun and Wei, Furu},
title = {TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models},
booktitle = {AAAI 2023},
year = {2023},
month = {February},
abstract = {Text recognition is a long-standing research problem for document digitalization. Existing approaches for text recognition are usually built based on CNN for image understanding and RNN for char-level text generation. In addition, another language model is usually needed to improve the overall accuracy as a post-processing step. In this paper, we propose an end-to-end text recognition approach with pre-trained image Transformer and text Transformer models, namely TrOCR, which leverages the Transformer architecture for both image understanding and wordpiece-level text generation. The TrOCR model is simple but effective, and can be pre-trained with large-scale synthetic data and fine-tuned with human-labeled datasets. Experiments show that the TrOCR model outperforms the current state-of-the-art models on both printed and handwritten text recognition tasks. The code and models will be publicly available at https://aka.ms/TrOCR},
url = {http://approjects.co.za/?big=en-us/research/publication/trocr-transformer-based-optical-character-recognition-with-pre-trained-models/},
}