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

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 \url{https://aka.ms/trocr}.

arXiv commentWork in Progress

References in corpus (6)

• Zero-Shot Text-to-Image Generation
• Unified Language Model Pre-training for Natural Language Understanding and Generation
• BEiT: BERT Pre-Training of Image Transformers
• Generating Synthetic Data for Text Recognition
• Rethinking Text Line Recognition Models
• Bidirectional Scene Text Recognition with a Single Decoder

Cited by in corpus (3)

• UTRNet: High-Resolution Urdu Text Recognition In Printed Documents
• Combining OCR Models for Reading Early Modern Printed Books
• Predicting the Past: Estimating Historical Appraisals with OCR and Machine Learning