A Method to Reduce Errors of String Recognition Based on Combination of Several Recognition Results with Per-Character Alternatives

DOI10.14529/MMP190307zbMath1437.68159OpenAlexW2999243473MaRDI QIDQ5212524

Konstantin Bulatovich Bulatov

Publication date: 29 January 2020

Published in: Bulletin of the South Ural State University. Series "Mathematical Modelling, Programming and Computer Software" (Search for Journal in Brave)

Full work available at URL: http://mathnet.ru/eng/vyuru506

zbMATH Keywords

recognition algorithmsmobile OCRrecognition in video stream

Mathematics Subject Classification ID

Pattern recognition, speech recognition (68T10) Algorithms on strings (68W32)

Uses Software

• ImageNet
• AlexNet

Cites Work

• Developments of machine learning schemes for dynamic time-wrapping-based speech recognition
• Modelling the Flow of Character Recognition Results in Video Stream
• Decision templates for multiple classifier fusion: An experimental comparison
• Unnamed Item
• Unnamed Item

This page was built for publication: A Method to Reduce Errors of String Recognition Based on Combination of Several Recognition Results with Per-Character Alternatives