Recent approaches in handwriting recognition with markovian modelling and recurrent neural networks

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Handwriting recognition is challenging because of the inherent variability of character shapes. Popular approaches for handwriting recognition are markovian and neuronal. Both approaches can take as input, sequences of frames obtained by sliding a window along a word or a text-line. We present markovian (Dynamic Bayesian Networks, Hidden Markov Models) and recurrent neural network-based approaches (RNNs) dedicated to character, word and text-line recognition. These approaches are applied to the recognition of both Latin and Arabic scripts.

Original languageEnglish
Title of host publicationRecent Advances of Neural Network Models and Applications - Proceedings of the 23rd Workshop of the Italian Neural Networks Society (SIREN)
Pages261-267
Number of pages7
DOIs
Publication statusPublished - 28 Mar 2014
Externally publishedYes
Event23rd Workshop of the Italian Neural Networks Society, WIRN 2013 - Vietri sul Mare, Salerno, Italy
Duration: 23 May 201324 May 2013

Publication series

NameSmart Innovation, Systems and Technologies
Volume26
ISSN (Print)2190-3018
ISSN (Electronic)2190-3026

Conference

Conference23rd Workshop of the Italian Neural Networks Society, WIRN 2013
Country/TerritoryItaly
CityVietri sul Mare, Salerno
Period23/05/1324/05/13

Keywords

  • BLSTMs
  • Hidden Markov Models
  • Recurrent neural networks
  • Text-line recognition
  • Word recognition

Fingerprint

Dive into the research topics of 'Recent approaches in handwriting recognition with markovian modelling and recurrent neural networks'. Together they form a unique fingerprint.

Cite this