scene-text-recognition

A collection of original, innovative ideas and algorithms towards Advanced Literate Machinery. This project is maintained by the OCR Team in the Language Technology Lab, Tongyi Lab, Alibaba Group.

ocr computer-vision artificial-intelligence text-recognition document text-detection document-analysis end-to-end-ocr multimodal scene-text-recognition multimodal-deep-learning scene-text-detection vision-language document-understanding scene-text-detection-recognition document-recognition document-intelligence documentai vision-language-transformer vision-language-model

UpdatedApr 9, 2025
C++

MhLiao /TextBoxes_plusplus

Star959

TextBoxes++: A Single-Shot Oriented Scene Text Detector

ocr scene-text scene-text-recognition scene-text-detection

UpdatedOct 22, 2023
C++

OpenOCR: A general OCR system with accuracy and efficiency. Supporting 24 Scene Text Recognition methods trained from scratch on large-scale real datasets, and will continue to add the latest methods.

ocr scene-text-recognition scene-text-detection ocr-pytorch chineseocr

UpdatedAug 27, 2025
Python

cs-chan /Total-Text-Dataset

Star761

Total Text Dataset. It consists of 1555 images with more than 3 different text orientations: Horizontal, Multi-Oriented, and Curved, one of a kind.

dataset text-recognition text-detection scene-text scene-text-recognition scene-text-detection text-detection-recognition icdar total-text curve-text

UpdatedOct 5, 2023
MATLAB

baudm /parseq

Star672

Scene Text Recognition with Permuted Autoregressive Sequence Models (ECCV 2022)

ocr computer-vision text-recognition optical-character-recognition eccv scene-text-recognition vision-transformer eccv2022

UpdatedMay 29, 2024
Python

Canjie-Luo /MORAN_v2

Star647

MORAN: A Multi-Object Rectified Attention Network for Scene Text Recognition

attention-mechanism image-rectification scene-text image-deformation scene-text-recognition

UpdatedJul 25, 2024
Python

jiangxiluning /FOTS.PyTorch

Star645

FOTS Pytorch Implementation

ocr scene-text-recognition cvpr2018

UpdatedFeb 14, 2023
Python

Bartzi /see

Star576

Code for the AAAI 2018 publication "SEE: Towards Semi-Supervised End-to-End Scene Text Recognition"

computer-vision deep-learning chainer cnn semi-supervised-learning scene-text-recognition

UpdatedApr 26, 2019
Python

clovaai /synthtiger

Star559

Official Implementation of SynthTIGER (Synthetic Text Image Generator), ICDAR 2021

ocr recognition deep-learning dataset text-recognition generation synthetic ocr-recognition scene-text scene-text-recognition icdar2021

UpdatedJun 14, 2024
Python

Media-Smart /vedastr

Star535

A scene text recognition toolbox based on PyTorch

ocr pytorch transformer text-recognition ocr-recognition scene-text-recognition

UpdatedSep 7, 2021
Python

wenwenyu /MASTER-pytorch

Star280

Code for the paper "MASTER: Multi-Aspect Non-local Network for Scene Text Recognition" (Pattern Recognition 2021)

ocr transformer scene-text-recognition self-attention non-local-network

UpdatedDec 26, 2021
Python

roatienza /straug

Star265

Image transformations designed for Scene Text Recognition (STR) data augmentation. Published at ICCV 2021 Workshop on Interactive Labeling and Data Augmentation for Vision.

str data-augmentation scene-text-recognition

UpdatedJun 24, 2024
Python

yeungchenwa /Recommendations-Diffusion-Text-Image

Star265

A paper collection of recent diffusion models for text-image generation tasks, e,g., visual text generation, font generation, text removal, text image super resolution, text editing, handwritten generation, scene text recognition and scene text detection.

awesome text super-resolution text-to-image handwritten text-editing scene-text-recognition scene-text-detection diffusion-models text-image font-generation text-removal