-
faster-CTPN - very fast CTPN https://github.com/hsddlz/faster-CTPN we change the LSTM model to conv1D that more than 5 times faster than the original version.
-
场景文字图像增广工具 https://github.com/Canjie-Luo/Scene-Text-Image-Transformer
场景文字去除数据集 https://github.com/HCIILAB/Scene-Text-Removal
场景文字检测与识别文献/代码大列表 https://github.com/Jyouhou/SceneTextPapers
Single Shot Text Detector with Regional Attention https://github.com/HotaekHan/SSTDNet
This is a pytorch re-implementation of EAST: An Efficient and Accurate Scene Text Detector. https://github.com/songdejia/EAST
场景文字识别与理解资源集锦 https://github.com/tangzhenyu/Scene-Text-Understanding
通过分割来检测文字 PixelLink: Detecting Scene Text via Instance Segmentation https://github.com/ZJULearning/pixel_link
ChineseAddress_OCR - Photographing Chinese-Address OCR implemented using CTPN+CTC+Address Correction. 拍照文档中文地址文字识别。 https://github.com/Walleclipse/ChineseAddress_OCR
任意方向场景文字检测 https://github.com/mjq11302010044/RRPN
AdvancedEAST高效场景文字检测 https://github.com/huoyijie/AdvancedEAST https://www.pyimagesearch.com/2018/08/20/opencv-text-detection-east-text-detector/
R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection https://github.com/beacandler/R2CNN
Tensorflow/Keras实现的端到端不定长中文字符检测和识别 https://github.com/YCG09/chinese_ocr
银行卡、身份证、门牌号光学识别 https://github.com/evilgix/Evil
文字识别(OCR)合成数据生成器 https://github.com/Belval/TextRecognitionDataGenerator
OCR文字(汉字)识别训练图像生成器 https://github.com/Sanster/text_renderer
准确率99.8%的开源车牌识别 https://github.com/zhubenfu/License-Plate-Detect-Recognition-via-Deep-Neural-Networks-accuracy-up-to-99.9
Talk the Walk: Navigating New York City through Grounded Dialogue(语音导航) https://github.com/facebookresearch/talkthewalk https://arxiv.org/abs/1807.03367
验证码识别 https://github.com/ecthros/uncaptcha2
ARU-Net: A Neural Pixel Labeler for Layout Analysis of Historical Documents https://github.com/TobiasGruening/ARU-Net
A tensorflow re-implementation of RRPN: Arbitrary-Oriented Scene Text Detection via Rotation Proposals. https://github.com/DetectionTeamUCAS/RRPN_Faster-RCNN_Tensorflow
Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes https://arxiv.org/abs/1807.02242 https://github.com/lvpengyuan/masktextspotter.caffe2
用web界面从PDF文件提取表格数据 https://github.com/camelot-dev/excalibur
基于深度学习的文字识别系统 https://github.com/AstarLight/CPS-OCR-Engine
Geometry-Aware Scene Text Detection with Instance Transformation Network https://github.com/zlmzju/itn
开源OCR文字识别软件Calamari https://github.com/Calamari-OCR/calamari
DeepTextSpotter: An End-to-End Trainable Scene Text Localization and Recognition Framework https://github.com/MichalBusta/DeepTextSpotter
yolo3+ocr https://github.com/chineseocr/chineseocr
Recognizing cropped text in natural images. https://github.com/bgshih/aster
Single Shot Scene Text Retrieval, ECCV 2018. https://github.com/lluisgomez/single-shot-str
Graph Convolutional Networks for Text Classification. AAAI 2019 https://github.com/yao8839836/text_gcn
A PyTorch implement of ECCV2018 Paper: TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes https://github.com/princewang1994/TextSnake.pytorch
ocr, cnn+lstm+ctc, crnn, recognition model, tensorflow https://github.com/Li-Ming-Fan/OCR-CRNN-CTC
CRNN(CNN+RNN+CTCLoss)中文手写汉字识别 https://github.com/chizhanyuefeng/Chinese_OCR_CNN-RNN-CTC
ICDAR 2017场景文字图像数据集(及最新结果列表) https://github.com/cs-chan/Total-Text-Dataset