Table detection has been an interesting and challenging problem in the field of document analyses. Object detection algorithms such as Faster-RCNN has been exploited so many times to detect tables in the documents. This is just another experiment but with a different architecture which is Mask_RCNN.

source code to ICLR'19, 'A Closer Look at Few-shot Classification'

deeplabv3plus (Google's new algorithm for semantic segmentation) in keras：Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

Trainable end-to-end full page text recognition

Table Detection using Deep Learning FasterRCNN

ICDAR 2019 Robust Reading Challenge on Scanned Receipts OCR and Information Extraction

Development repo for ICDAR 2019 Robust Reading Challenge on Scanned Receipts OCR and Information Extraction

Code for paper Unsupervised Object Segmentation by Redrawing

Text Detection by RetinaNet with PyTorch (Code will be released soon)

3rd of Task3 and 4th of Task4 of StructSeg2019 competition - MICCAI 2019

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.

Segmentation models with pretrained backbones. Keras.

Handwritten Text Recognition (HTR) system implemented with TensorFlow.

FOTS text detection branch reimplementation, hmean: 83.3%

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

Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation