Publication

Back to overview

Exploiting State-of-the-Art Deep Learning Methods for Document Image Analysis

Type of publication Peer-reviewed
Publikationsform Original article (peer-reviewed)
Author Pondenkandath Vinaychandran, Seuret Mathias, Ingold Rolf, Afzal Muhammad Zeshan, Liwicki Marcus,
Project HisDoc III : Large-Scale Historical Document Classification
Show all

Original article (peer-reviewed)

Journal 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR)
Volume (Issue) 05
Page(s) 30 - 35
Title of proceedings 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR)
DOI 10.1109/icdar.2017.325

Abstract

This paper provides details of our (partially award-winning) methods submitted to four competitions of ICDAR 2017. In particular, they are designed to (i) classify scripts, (ii) perform pixel-based labeling for layout analysis, (iii) identify writers, and (iv) recognize font size and types. The methods build on the current state-of-the-art in Deep Learning and have been adapted to the specific needs of the individual tasks. All methods are variants of Convolutional Neural Network (CNN) with specialized architectures, initialization, and other tricks which have been introduced in the field of deep learning within the last few years.
-