A tensorflow siamese network implementation. Illustrated using singature recognition/identification.

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

Code and procdures for handwriting object detection and recognition

Tools necessary to perform a multi-fold pretrained voting approach utlizing OCRopus.

Online-handwritten version of the George Washington Dataset.

~1000 book pages + OpenCV + python = page regions identified as paragraphs, lines, images, captions, etc.

A synthetic data generator for text recognition

A repository with anonymized invoices

A selection of test lines of several early printed books as well as the corresponding individual OCRopus models and mixed models.

Creates synthetic degraded image documents that could be used to train Neural Networks

A tensorflow reproducing of paper “Editing Text in the wild”

CORD: A Consolidated Receipt Dataset for Post-OCR Parsing

Total Text Dataset - ICDAR 2017. It consists of 1555 images with more than 3 different text orientations: Horizontal, Multi-Oriented, and Curved, one of a kind.

TDF-ICDAR 2019 Dataset for Typeset Math Formula Detection

Dataset for scene text removal

This Web application crawls PDFs from governement websites, performs table detection and displays advanced statistics.

Generate text images for training deep learning ocr model

Distorted Document Images dataset (DDI-100).

ScrabbleGAN: Semi-Supervised Varying Length Handwritten Text Generation (CVPR20)