Offline Handwritten Text Recognition Using Support Vector Machines

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F17%3APU122894" target="_blank" >RIV/00216305:26220/17:PU122894 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/8049930" target="_blank" >https://ieeexplore.ieee.org/document/8049930</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/SPIN.2017.8049930" target="_blank" >10.1109/SPIN.2017.8049930</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Offline Handwritten Text Recognition Using Support Vector Machines

Popis výsledku v původním jazyce

Comenia script is a novel handwritten text introduced at primary schools in the Czech Republic. This paper describes a method for handwritten text recognition (HWR) of this font. In particular it proposes a method for preprocessing and normalization of data and optical character recognition based on SVM classifier. We have trained and statistically evaluated several models, where we have focused on recognition of different styles of writing of the same characters - for the forensic purposes and identification of the author of a document. The best model has achieved 92.86 % accuracy without any further postprocessing, e.g. a spellchecker. We also proposed using more than one classification model for character recognition that has shown to increase accuracy when compared to a single model approach.

Název v anglickém jazyce

Offline Handwritten Text Recognition Using Support Vector Machines

Popis výsledku anglicky

Comenia script is a novel handwritten text introduced at primary schools in the Czech Republic. This paper describes a method for handwritten text recognition (HWR) of this font. In particular it proposes a method for preprocessing and normalization of data and optical character recognition based on SVM classifier. We have trained and statistically evaluated several models, where we have focused on recognition of different styles of writing of the same characters - for the forensic purposes and identification of the author of a document. The best model has achieved 92.86 % accuracy without any further postprocessing, e.g. a spellchecker. We also proposed using more than one classification model for character recognition that has shown to increase accuracy when compared to a single model approach.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/LO1401" target="_blank" >LO1401: Interdisciplinární výzkum bezdrátových technologií</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2017

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2017 4th International Conference on Signal Processing and Integrated Networks (SPIN)

ISBN

978-1-5090-2796-5

ISSN

—

e-ISSN

—

Počet stran výsledku

5

Strana od-do

132-136

Název nakladatele

Neuveden

Místo vydání

Neuveden

Místo konání akce

Dept. of ECE, ASET, Amity University, Noida Sec-

Datum konání akce

2. 2. 2017

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000426076800027