Chargrid-OCR: End-to-end Trainable Optical Character Recognition for Printed Documents using Instance Segmentation release_ehc3wyggt5cojib4mdgan2w7x4

by Christian Reisswig, Anoop R Katti, Marco Spinaci, Johannes Höhne

Released as a article .

2019  

Abstract

We present an end-to-end trainable approach for Optical Character Recognition (OCR) on printed documents. Specifically, we propose a model that predicts a) a two-dimensional character grid (chargrid) representation of a document image as a semantic segmentation task and b) character boxes for delineating character instances as an object detection task. For training the model, we build two large-scale datasets without resorting to any manual annotation - synthetic documents with clean labels and real documents with noisy labels. We demonstrate experimentally that our method, trained on the combination of these datasets, (i) outperforms previous state-of-the-art approaches in accuracy (ii) is easily parallelizable on GPU and is, therefore, significantly faster and (iii) is easy to train and adapt to a new domain.
In text/plain format

Archived Files and Locations

application/pdf  695.2 kB
file_htqni3wks5bohlr4xnku5x37wa
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2019-09-13
Version   v2
Language   en ?
arXiv  1909.04469v2
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 6e2fdbc1-6749-4f77-b8df-5f07fff59cd8
API URL: JSON