Cellular wave computer algorithms with spatial semantic embedding for handwritten text recognition

Kristóf Karacs, Gábor Prószéky, T. Roska

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

The recognition of cursive handwritten texts is a complex, in some cases unsolvable, task. One problem is that in most cases it is difficult or impossible to identify each letter, even if the words are separated. In our new method, the identification of letters is not needed due to the extensive and iterative use of semantic and morphological information of a given language. We are using a spatial feature code, generated by a cellular nonlinear network (CNN) based cellular wave computer algorithm, and combine it with the linguistic properties of the given language. Most general-purpose handwriting recognition systems lack the ability to integrate linguistic background knowledge because they use it only for post-processing recognition results. The high-level a priori background knowledge is, however, crucial in human readingand similarly it can boost recognition rates dramatically in case of recognition systems. In our new system we do not treat the visual source as the only input: Geometric and linguistic information are given equal importance. On the geometric side we use word-level holistic feature detection without letter segmentation by analogic CNN algorithms designed for cellular wave computers (IEEE Trans. Circuits Syst. 1993; 40:163-173; Cellular Neural Networks and Visual Computing, Foundations and Applications. Cambridge University Press: Cambridge, U.K., New York, 2002). The linguistic side is based on a morpho-syntactic linguistic system (Proceedings of COLING-2002, vol. II, Taipei, Taiwan, 2002; 1263-1267). A novel shape coding method is used to interface them, and their interaction is enhanced via an inverse filtering technique based on features that are global or of a low confidence value. A statistical context selection method is also applied to further reduce the output word lists.

Original languageEnglish
Pages (from-to)1019-1050
Number of pages32
JournalInternational Journal of Circuit Theory and Applications
Volume37
Issue number10
DOIs
Publication statusPublished - Dec 2009

Fingerprint

Linguistics
Semantics
Nonlinear networks
Handwriting Recognition
Feature Detection
Cellular neural networks
Taiwan
Network Algorithms
Syntactics
Cellular Networks
Post-processing
Confidence
Segmentation
Filtering
Coding
Integrate
Text
Neural Networks
Networks (circuits)
Computing

Keywords

  • Cellular wave computer
  • Handwriting recognition
  • Lexicon reduction
  • Semantic embedding

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials
  • Computer Science Applications
  • Applied Mathematics

Cite this

Cellular wave computer algorithms with spatial semantic embedding for handwritten text recognition. / Karacs, Kristóf; Prószéky, Gábor; Roska, T.

In: International Journal of Circuit Theory and Applications, Vol. 37, No. 10, 12.2009, p. 1019-1050.

Research output: Contribution to journalArticle

@article{5f387a3dccda4eefade4daffc76e7140,
title = "Cellular wave computer algorithms with spatial semantic embedding for handwritten text recognition",
abstract = "The recognition of cursive handwritten texts is a complex, in some cases unsolvable, task. One problem is that in most cases it is difficult or impossible to identify each letter, even if the words are separated. In our new method, the identification of letters is not needed due to the extensive and iterative use of semantic and morphological information of a given language. We are using a spatial feature code, generated by a cellular nonlinear network (CNN) based cellular wave computer algorithm, and combine it with the linguistic properties of the given language. Most general-purpose handwriting recognition systems lack the ability to integrate linguistic background knowledge because they use it only for post-processing recognition results. The high-level a priori background knowledge is, however, crucial in human readingand similarly it can boost recognition rates dramatically in case of recognition systems. In our new system we do not treat the visual source as the only input: Geometric and linguistic information are given equal importance. On the geometric side we use word-level holistic feature detection without letter segmentation by analogic CNN algorithms designed for cellular wave computers (IEEE Trans. Circuits Syst. 1993; 40:163-173; Cellular Neural Networks and Visual Computing, Foundations and Applications. Cambridge University Press: Cambridge, U.K., New York, 2002). The linguistic side is based on a morpho-syntactic linguistic system (Proceedings of COLING-2002, vol. II, Taipei, Taiwan, 2002; 1263-1267). A novel shape coding method is used to interface them, and their interaction is enhanced via an inverse filtering technique based on features that are global or of a low confidence value. A statistical context selection method is also applied to further reduce the output word lists.",
keywords = "Cellular wave computer, Handwriting recognition, Lexicon reduction, Semantic embedding",
author = "Krist{\'o}f Karacs and G{\'a}bor Pr{\'o}sz{\'e}ky and T. Roska",
year = "2009",
month = "12",
doi = "10.1002/cta.485",
language = "English",
volume = "37",
pages = "1019--1050",
journal = "International Journal of Circuit Theory and Applications",
issn = "0098-9886",
publisher = "John Wiley and Sons Ltd",
number = "10",

}

TY - JOUR

T1 - Cellular wave computer algorithms with spatial semantic embedding for handwritten text recognition

AU - Karacs, Kristóf

AU - Prószéky, Gábor

AU - Roska, T.

PY - 2009/12

Y1 - 2009/12

N2 - The recognition of cursive handwritten texts is a complex, in some cases unsolvable, task. One problem is that in most cases it is difficult or impossible to identify each letter, even if the words are separated. In our new method, the identification of letters is not needed due to the extensive and iterative use of semantic and morphological information of a given language. We are using a spatial feature code, generated by a cellular nonlinear network (CNN) based cellular wave computer algorithm, and combine it with the linguistic properties of the given language. Most general-purpose handwriting recognition systems lack the ability to integrate linguistic background knowledge because they use it only for post-processing recognition results. The high-level a priori background knowledge is, however, crucial in human readingand similarly it can boost recognition rates dramatically in case of recognition systems. In our new system we do not treat the visual source as the only input: Geometric and linguistic information are given equal importance. On the geometric side we use word-level holistic feature detection without letter segmentation by analogic CNN algorithms designed for cellular wave computers (IEEE Trans. Circuits Syst. 1993; 40:163-173; Cellular Neural Networks and Visual Computing, Foundations and Applications. Cambridge University Press: Cambridge, U.K., New York, 2002). The linguistic side is based on a morpho-syntactic linguistic system (Proceedings of COLING-2002, vol. II, Taipei, Taiwan, 2002; 1263-1267). A novel shape coding method is used to interface them, and their interaction is enhanced via an inverse filtering technique based on features that are global or of a low confidence value. A statistical context selection method is also applied to further reduce the output word lists.

AB - The recognition of cursive handwritten texts is a complex, in some cases unsolvable, task. One problem is that in most cases it is difficult or impossible to identify each letter, even if the words are separated. In our new method, the identification of letters is not needed due to the extensive and iterative use of semantic and morphological information of a given language. We are using a spatial feature code, generated by a cellular nonlinear network (CNN) based cellular wave computer algorithm, and combine it with the linguistic properties of the given language. Most general-purpose handwriting recognition systems lack the ability to integrate linguistic background knowledge because they use it only for post-processing recognition results. The high-level a priori background knowledge is, however, crucial in human readingand similarly it can boost recognition rates dramatically in case of recognition systems. In our new system we do not treat the visual source as the only input: Geometric and linguistic information are given equal importance. On the geometric side we use word-level holistic feature detection without letter segmentation by analogic CNN algorithms designed for cellular wave computers (IEEE Trans. Circuits Syst. 1993; 40:163-173; Cellular Neural Networks and Visual Computing, Foundations and Applications. Cambridge University Press: Cambridge, U.K., New York, 2002). The linguistic side is based on a morpho-syntactic linguistic system (Proceedings of COLING-2002, vol. II, Taipei, Taiwan, 2002; 1263-1267). A novel shape coding method is used to interface them, and their interaction is enhanced via an inverse filtering technique based on features that are global or of a low confidence value. A statistical context selection method is also applied to further reduce the output word lists.

KW - Cellular wave computer

KW - Handwriting recognition

KW - Lexicon reduction

KW - Semantic embedding

UR - http://www.scopus.com/inward/record.url?scp=73949089643&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=73949089643&partnerID=8YFLogxK

U2 - 10.1002/cta.485

DO - 10.1002/cta.485

M3 - Article

VL - 37

SP - 1019

EP - 1050

JO - International Journal of Circuit Theory and Applications

JF - International Journal of Circuit Theory and Applications

SN - 0098-9886

IS - 10

ER -