Papers
arxiv:2109.10282

TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models

Published on Sep 21, 2021
Authors:
,
,
,
,
,
,
,

Abstract

Text recognition is a long-standing research problem for document digitalization. Existing approaches 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 the printed, handwritten and scene text recognition tasks. The TrOCR models and code are publicly available at https://aka.ms/trocr.

Community

Sign up or log in to comment

Models citing this paper 37

Browse 37 models citing this paper

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2109.10282 in a dataset README.md to link it from this page.

Spaces citing this paper 328

Collections including this paper 12