Original title: Classification of Czech sign language alphabet letters using cnn – preliminary study
Authors: Krejsa, Jiří ; Věchet, Stanislav
Document type: Papers
Conference/Event: International Conference Engineering Mechanics 2020 /26./, Brno (CZ), 20201124
Year: 2020
Language: eng
Abstract: Abstract: The paper deals with the classification of Czech sign language single hand alphabet letters from static images using convolutional neural network (CNN). Proposed CNN architecture exhibits about 71% successful rate of classifying the letters signed by the person not included in the training data set.
Keywords: classification; convolution neural network; sign language
Host item entry: ENGINEERING MECHANICS 2020, ISBN 978-80-214-5896-3, ISSN 1805-8248

Institution: Institute of Thermomechanics AS ČR (web)
Document availability information: Fulltext is available at the institute of the Academy of Sciences.
Original record: http://hdl.handle.net/11104/0316611

Permalink: http://www.nusl.cz/ntk/nusl-433443


The record appears in these collections:
Research > Institutes ASCR > Institute of Thermomechanics
Conference materials > Papers