rkshuai

AttentionOCR

Scene text recognition

research-charnet

CharNet: Convolutional Character Networks

MetaPruning

MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning. In ICCV 2019.

doc3D-dataset

A hybrid dataset for document unwarping (Paper: https://www3.cs.stonybrook.edu/~cvl/projects/dewarpnet/storage/paper.pdf)

DewarpNet

Code for the paper "DewarpNet: Single-Image Document Unwarping With Stacked 3D and 2D Regression Networks" (ICCV '19)

stela

Scene Text Detection with Learned Anchor

Thinning-Algorithms

A repository containing implementation of 4 thinning algorithms - Zhang Suen, Stentiford, Lu Wang, Hilditch. Performance of the algorithms are tested on Handwritten Kannada Characters

MaskTextSpotter

A PyTorch implementation of Mask TextSpotter

PubLayNet

TableBank

TableBank: A Benchmark Dataset for Table Detection and Recognition

DocCreator

DIAR software for synthetic document image and groundtruth generation, with various degradation models for data augmentation

Box_Discretization_Network

Omnidirectional Scene Text Detection with Sequential-free Box Discretization (IJCAI 2019). Including competition model, online demo, etc.

Text-Image-Augmentation

Geometric Augmentation for Text Image

ShuffleNet-Series

AnchorFreeDetection

list the paper for recently anchor free detector

aster.pytorch

ASTER in Pytorch

corner

Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation

GANimation

GANimation: Anatomically-aware Facial Animation from a Single Image (ECCV'18 Oral) [PyTorch]

Deep-Flow-Guided-Video-Inpainting

pytorch implementation for "Deep Flow-Guided Video Inpainting"(CVPR'19)

CRAFT-pytorch

Official implementation of Character Region Awareness for Text Detection (CRAFT)

baiduyun_deeplearning_competition

百度云魅族深度学习应用大赛

mathAI

一个拍照做题程序。输入一张包含数学计算题的图片，输出识别出的数学计算式以及计算结果。This is a mathematic expression recognition project.

OCR_detection_IC15

OCR detection for ICDAR2015, which is based on FOTS, the precision is 80.6%.

MNN

MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba

StegaStamp

Invisible Hyperlinks in Physical Photographs

TextImageGenerator

该脚本根据语料文件生成对应的图像文件，适用于文本识别等CV任务

shadowsocks_install

Auto Install Shadowsocks Server for CentOS/Debian/Ubuntu

arxiv-sanity-preserver

Web interface for browsing, search and filtering recent arxiv submissions

tf_doc_localisation

996.ICU

Repo for counting stars and contributing. Press F to pay respect to glorious developers.