Chargrid: Towards Understanding 2D Documents (2018-09-24T00:00:00.000000Z)

TL;DR

A novel type of text representation is introduced that preserves the 2D layout of a document by encoding each document page as a two-dimensional grid of characters and it is shown that it significantly outperforms approaches based on sequential text or document images.

Abstract

We introduce a novel type of text representation that preserves the 2D layout of a document. This is achieved by encoding each document page as a two-dimensional grid of characters. Based on this representation, we present a generic document understanding pipeline for structured documents. This pipeline makes use of a fully convolutional encoder-decoder network that predicts a segmentation mask and bounding boxes. We demonstrate its capabilities on an information extraction task from invoices and show that it significantly outperforms approaches based on sequential text or document images.

Authors

Anoop R. Katti

1 papers

C. Reisswig

1 papers

Cordula Guder

1 papers

TL;DR

Abstract

Authors

References30 items

Minimum Word Error Rate Training for Attention-Based Sequence-to-Sequence Models

Real-Time Document Localization in Natural Images by Recursive Application of a CNN

CloudScan - A Configuration-Free Invoice Analysis System Using Recurrent Neural Networks

Document Image Binarization with Fully Convolutional Neural Networks

Focal Loss for Dense Object Detection

Learning to Extract Semantic Structure from Documents Using Multimodal Fully Convolutional Neural Networks

ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation

Learning to Refine Object Segments

Neural Architectures for Named Entity Recognition

Multilingual Language Processing From Bytes

Multi-Scale Context Aggregation by Dilated Convolutions

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

A Neural Attention Model for Abstractive Sentence Summarization

Page segmentation of historical document images with convolutional autoencoders

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

U-Net: Convolutional Networks for Biomedical Image Segmentation

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification

Efficient object localization using Convolutional Networks

Very Deep Convolutional Networks for Large-Scale Image Recognition

Neural Machine Translation by Jointly Learning to Align and Translate

Convolutional Neural Networks for Sentence Classification

Learning Rich Features from RGB-D Images for Object Detection and Segmentation

Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation

Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks

ImageNet classification with deep convolutional neural networks

Offline Handwriting Recognition with Multidimensional Recurrent Neural Networks

Segmentation

Offline Handwriting Recognition with Multidimensional Recurrent Neural Networks

Gradient-based learning applied to document recognition

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names