Historical Alphabet Transliteration Software Using Computer Vision Classification Approach
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F60460709%3A41110%2F22%3A91368" target="_blank" >RIV/60460709:41110/22:91368 - isvavai.cz</a>
Result on the web
<a href="https://www.openpublish.eu/" target="_blank" >https://www.openpublish.eu/</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-031-09076-9_4" target="_blank" >10.1007/978-3-031-09076-9_4</a>
Alternative languages
Result language
čeština
Original language name
Historical Alphabet Transliteration Software Using Computer Vision Classification Approach
Original language description
The article presents the problem of developing mobile software for classification and automatic transliteration of historical alphabets to Latin alphabet using OCR Computer Vision algorithms and is presented on Palmyrene Alphabet. Our suggested solution of semi-automatic transliteration of historical alphabets speeds up and simplifies the process of ancient text analysis and makes reading historical alphabets available to the public. We created a mobile application template for field use and proved the functionality on our own photographic and digitized hand-written datasets of Palmyrene letters, using a MobileNet Artificial Neural Network for character recognition. Such an application helps archaeologists with a faster character transliteration of newly discovered, archived, but untranslated tablets, columns etc., and for checking hand-transliterated texts.
Czech name
Historical Alphabet Transliteration Software Using Computer Vision Classification Approach
Czech description
The article presents the problem of developing mobile software for classification and automatic transliteration of historical alphabets to Latin alphabet using OCR Computer Vision algorithms and is presented on Palmyrene Alphabet. Our suggested solution of semi-automatic transliteration of historical alphabets speeds up and simplifies the process of ancient text analysis and makes reading historical alphabets available to the public. We created a mobile application template for field use and proved the functionality on our own photographic and digitized hand-written datasets of Palmyrene letters, using a MobileNet Artificial Neural Network for character recognition. Such an application helps archaeologists with a faster character transliteration of newly discovered, archived, but untranslated tablets, columns etc., and for checking hand-transliterated texts.
Classification
Type
D - Article in proceedings
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
Article name in the collection
Lecture Notes in Networks and Systems Volume 502
ISBN
978-303109075-2
ISSN
—
e-ISSN
—
Number of pages
12
Pages from-to
34-45
Publisher name
Springer
Place of publication
Springer Science and Business Media Deutschland
Event location
online
Event date
Apr 26, 2022
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—