scene-text-recognition

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

Text recognition (optical character recognition) with deep learning methods.

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

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

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

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

FOTS Pytorch Implementation

A scene text recognition toolbox based on PyTorch

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

Scene text detection and recognition based on Extremal Region(ER)

text_recognition_toolbox: The reimplementation of a series of classical scene text recognition papers with Pytorch in a uniform way.

MASTER

Code for the paper "KISS: Keeping it Simple for Scene Text Recognition"

Convolutional Recurrent Neural Network(CRNN) for End-to-End Text Recognition - TensorFlow 2

multi-task learning for text recognition with joint CTC-attention

Convolutional recurrent neural network for scene text recognition or OCR in Keras

H. Zhang, Q. Yao, M. Yang, Y. Xu, X. Bai. AutoSTR: Efficient Backbone Search for Scene Text Recognition. European Conference on Computer Vision (ECCV). 2020.

A flexible Python front-end inference SDK based on TensorRT

Official implementation of SynthTIGER (Synthetic Text Image GEneratoR) ICDAR 2021

Scene Text Recognition (STR) methods trained with fewer real labels.

End-to-end pipeline for real-time scene text detection and recognition.

This is a c++ project deploying a deep scene text reading pipeline with tensorflow. It reads text from natural scene images. It uses frozen tensorflow graphs. The detector detect scene text locations. The recognizer reads word from each detected bounding box.

A curated list of papers and resources for scene text detection and recognition

TensorFlow Implementation of FOTS, Fast Oriented Text Spotting with a Unified Network.

Dictionary-guided Scene Text Recognition (CVPR-2021)

Tracking the latest progress in Scene Text Detection and Recognition: Must-read papers well organized with code and dataset

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

a math-formula image recognition project which placed at the first place in a competition hosted by NAVER CONNECT boostcamp AI Tech

Implement 'Image deformation using moving least squares' with pybind11 and python3 and opencv2

Improved Text recognition algorithms on different text domains like scene text, handwritten, document, Chinese/English, even ancient books