Methods › Computer Vision › OCR Models › TrOCR

TrOCR

11 papers tagged archive 2025-07-28

Introduced by Minghao Li et al. in TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

TrOCR is an end-to-end Transformer-based OCR model for text recognition with pre-trained CV and NLP models. It leverages the Transformer architecture for both image understanding and wordpiece-level text generation. It first resizes the input text image into 384 × 384 and then the image is split into a sequence of 16 patches which are used as the input to image Transformers. Standard Transformer architecture with the self-attention mechanism is leveraged on both encoder and decoder parts, where wordpiece units are generated as the recognized text from the input image.

PaperSource

Papers archive 2025-07-28

11 shown of 11, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Optical Character Recognition7
Optical Character Recognition (OCR)7
HTR4
Handwritten Text Recognition3
Decoder2
Language Modeling2
Language Modelling2
Transfer Learning2
Adversarial Attack1
Data Augmentation1
Image Captioning1
Image Generation1
Large Language Model1
NER1
Named Entity Recognition1
Named Entity Recognition (NER)1
Outlier Detection1
Scene Text Recognition1
Text Generation1
named-entity-recognition1

Usage over time archive 2025-07-28

Papers per year tagged with TrOCR: 2021 to 2025, peak 3 3 0 2021: 1 paper 2021 2022: 2 papers 2022 2023: 2 papers 2023 2024: 3 papers 2024 2025: 3 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (11 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

OCR Models

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections