Combine Textboxes++ and RetinaNet which used to replace the original 'neck' network SSD for scene text localization.

Code for my ICDAR paper "Deep Visual Template-Free Form Parsing"

SSD,python,pytorch

document image analysis

A neural network that transforms a screenshot into a static website

Table Detection in Documents using Faster-RCNN

patchwise semantic segmentation

DFKI Layout Detection for OCR-D

Document Understanding tools

Building models for Optical Character Recognition

An example of text object detection

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

This is a keras implementation of PhocNet

PyTorch implementation of DeepLabv3

Master thesis project, aims to classify a scanned document, combining the physical segmentation phase and the logical segmentation phase

Text line segmentation using Mask R-CNN

a deep learning model for page layout analysis / segmentation.