An improved classifier and transliterator of hand-written Palmyrene letters to Latin
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F60460709%3A41110%2F22%3A94074" target="_blank" >RIV/60460709:41110/22:94074 - isvavai.cz</a>
Result on the web
<a href="http://nnw.cz/obsahy22.html" target="_blank" >http://nnw.cz/obsahy22.html</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.14311/NNW.2022.32.011" target="_blank" >10.14311/NNW.2022.32.011</a>
Alternative languages
Result language
angličtina
Original language name
An improved classifier and transliterator of hand-written Palmyrene letters to Latin
Original language description
This article presents the problem of improving the classifier of handwritten letters from historical alphabets, using letter classification algorithms and transliterating them to Latin. We apply it on Palmyrene alphabet, which is a complex alphabet with letters, some of which are very similar to each other. We created a mobile application for Palmyrene alphabet that is able to transliterate hand-written letters or letters that are given as photograph images. At first, the core of the application was based on MobileNet, but the classification results were not suitable enough. In this article, we suggest an improved, better performing convolutional neural network architecture for hand-written letter classifier used in our mobile application. Our suggested new convolutional neural network architecture shows an improvement in accuracy from 0,6893 to 0,9821 by 142 % for hand-written model in comparison with the original MobileNet. Future plans are to improve the photographic model as well.
Czech name
—
Czech description
—
Classification
Type
J<sub>imp</sub> - Article in a specialist periodical, which is included in the Web of Science database
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2022
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
Neural Network World
ISSN
1210-0552
e-ISSN
1210-0552
Volume of the periodical
32
Issue of the periodical within the volume
4 2022
Country of publishing house
CZ - CZECH REPUBLIC
Number of pages
15
Pages from-to
181-195
UT code for WoS article
000912363100001
EID of the result in the Scopus database
2-s2.0-85147326925