Search awesome repositories

PyTorch Re-Implementation of EAST: An Efficient and Accurate Scene Text Detector

A PyTorch implementation of "ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network" (CVPR 2020 oral)

a Deep Learning Framework for Text https://delft.readthedocs.io/

Document Layout Analysis

Tools for manipulating and evaluating the hOCR format for representing multi-lingual OCR results by embedding them into HTML.

A PyTorch implementation of Mask TextSpotter

Generic framework for historical document processing

OCR, Scene-Text-Understanding, Text Recognition

CNN+LSTM+CTC based OCR implemented using tensorflow.

Use Convolutional Recurrent Neural Network to recognize the Handwritten line text image without pre segmentation into words or characters. Use CTC loss Function to train.

OCR system for Arabic language that converts images of typed text to machine-encoded text.

Unofficial implementation of "TableNet: Deep Learning model for end-to-end Table detection and Tabular data extraction from Scanned Document Images"

No description.

Pytorch implementation for "Decoupled attention network for text recognition".

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

Handwritten Text Recognition

Python library to extract tabular data from images and scanned PDFs

Extract tables from scanned image PDFs using Optical Character Recognition.

Packaged, Pytorch-based, easy to use, cross-platform version of the CRAFT text detector

Detect handwritten words (classic image processing based method).

Ocular is a state-of-the-art historical OCR system.

Detect and fix skew in images containing text

The code of "Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes"

Synthetic Scene Text from 3D Engines

Single Shot Text Detector with Regional Attention

Implementation of EAST scene text detector in Keras

Validate and transform various OCR file formats (hOCR, ALTO, PAGE, FineReader)

A semi-automatic open-source tool for Layout Analysis and Region EXtraction on early printed books.

Dewarping Document Image By Displacement Flow Estimation with Fully Convolutional Network

Deep learning based page layout analysis