DocReader: Bounding-Box Free Training of a Document Information Extraction Model

05/10/2021
by   Shachar Klaiman, et al.
0

Information extraction from documents is a ubiquitous first step in many business applications. During this step, the entries of various fields must first be read from the images of scanned documents before being further processed and inserted into the corresponding databases. While many different methods have been developed over the past years in order to automate the above extraction step, they all share the requirement of bounding-box or text segment annotations of their training documents. In this work we present DocReader, an end-to-end neural-network-based information extraction solution which can be trained using solely the images and the target values that need to be read. The DocReader can thus leverage existing historical extraction data, completely eliminating the need for any additional annotations beyond what is naturally available in existing human-operated service centres. We demonstrate that the DocReader can reach and surpass other methods which require bounding-boxes for training, as well as provide a clear path for continual learning during its deployment in production.

READ FULL TEXT

page 1

page 2

page 3

page 4

04/28/2021

Segmentation-Based Bounding Box Generation for Omnidirectional Pedestrian Detection

We propose a segmentation-based bounding box generation method for omnid...
11/28/2021

CHARTER: heatmap-based multi-type chart data extraction

The digital conversion of information stored in documents is a great sou...
11/26/2020

SelfText Beyond Polygon: Unconstrained Text Detection with Box Supervision and Dynamic Self-Training

Although a polygon is a more accurate representation than an upright bou...
04/05/2022

Text Spotting Transformers

In this paper, we present TExt Spotting TRansformers (TESTR), a generic ...
10/24/2018

Resolving Referring Expressions in Images With Labeled Elements

Images may have elements containing text and a bounding box associated w...
12/11/2018

Loss Guided Activation for Action Recognition in Still Images

One significant problem of deep-learning based human action recognition ...
03/17/2022

deepNIR: Datasets for generating synthetic NIR images and improved fruit detection system using deep learning techniques

This paper presents datasets utilised for synthetic near-infrared (NIR) ...