Detail publikace

Handwriting Comenia Script Recognition with Convolutional Neural Network

RAJNOHA, M. BURGET, R. DUTTA, M.

Originální název

Handwriting Comenia Script Recognition with Convolutional Neural Network

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

This paper deals with handwriting recognition (HWR) using artificial intelligence of so–called Comenia script - a modern handwritten font similar to block letters recently introduced at primary schools in the Czech Republic. This work describes a method how to extend a limited training set of handwritten letters and proposes a new method to increase stability and accuracy by artificially created image samples. We examined a large set of algorithms including a deep learning method for classification of the handwriting characters. The best results were achieved using a convolutional neural network, which achieved the accuracy or character recognition 90.04%

Klíčová slova

CNN; deep learning; handwriting recognition; HWR; OCR

Autoři

RAJNOHA, M.; BURGET, R.; DUTTA, M.

Vydáno

6. 7. 2017

Místo

Barcelona

ISBN

978-1-5090-3981-4

Kniha

40th Anniversary of International Conference on Telecommunications and Signal Processing (TSP)

Strany od

775

Strany do

779

Strany počet

5

URL

https://ieeexplore.ieee.org/document/8076093

BibTex

@inproceedings{BUT137770,
  author="Martin {Rajnoha} and Radim {Burget} and Malay Kishore {Dutta}",
  title="Handwriting Comenia Script Recognition with Convolutional Neural Network",
  booktitle="40th Anniversary of International Conference on Telecommunications and Signal Processing (TSP)",
  year="2017",
  pages="775--779",
  address="Barcelona",
  doi="10.1109/TSP.2017.8076093",
  isbn="978-1-5090-3981-4",
  url="https://ieeexplore.ieee.org/document/8076093"
}