Code and Data for ICDAR 2019 paper: Content Extraction from Lecture Video via Speaker Action Classification based on Pose Information

Detectron2 for Document Layout Analysis

patchwise semantic segmentation

This tool can detect textline of given image and write the output in a page xml data.

FreeAnchor: Learning to Match Anchors for Visual Object Detection (NeurIPS 2019)

Code for Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells, CVPR '19

FCDenseNet implementation for Table Localization

TensorFlow implementation of a segmentation system for document images.

This is a tool for pixel wise segmentation. This is developed in order to do use cases like page extraction, textline , word and structure recognition of library documents.

Adversarial Generation of Handwritten Text Images

very fast CTPN

Code and data for the paper at http://arxiv.org/abs/2004.07317

Distorted Document Images dataset (DDI-100).

DANet: Divergent Activation for Weakly Supervised Object Localization，in ICCV 2019

SSD: Single Shot MultiBox Detector | a PyTorch Tutorial to Object Detection

Document Understanding tools

FOTS text detection branch reimplementation, hmean: 83.3%

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

Implementation of our paper 'PixelLink: Detecting Scene Text via Instance Segmentation' in AAAI2018