Analysis of hierarchically-temporal dependencies for handwritten symbols and gestures recognition

Yulia Bolotova, Vladimir Spitsyn

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

This work represents a biologically inspired approach to object recognition based on analysis of hierarchical and temporal data dependencies. The article describes the hierarchical temporal memory model (HTM) and its optimization for object recognition task. Optimization includes Gabor and Canny filter image preprocessing, which makes the model suitable for handwritten symbols and gestures recognition; using of additional clustering on the stage of spatial pooling, a new proposed temporal grouping algorithm increases the overall recognition accuracy of the model; a new genetic algorithm was designed for searching the optimal parameters of the model.

Original languageEnglish
Title of host publicationProceedings - 2012 7th International Forum on Strategic Technology, IFOST 2012
DOIs
Publication statusPublished - 2012
Event2012 7th International Forum on Strategic Technology, IFOST 2012 - Tomsk, Russian Federation
Duration: 18 Sep 201221 Sep 2012

Other

Other2012 7th International Forum on Strategic Technology, IFOST 2012
CountryRussian Federation
CityTomsk
Period18.9.1221.9.12

Fingerprint

Gesture recognition
Object recognition
Genetic algorithms
Data storage equipment
Symbol

Keywords

  • gesture recognition
  • hierarchical temporal memory
  • symbols recognition
  • temporal grouping

ASJC Scopus subject areas

  • Management of Technology and Innovation

Cite this

Bolotova, Y., & Spitsyn, V. (2012). Analysis of hierarchically-temporal dependencies for handwritten symbols and gestures recognition. In Proceedings - 2012 7th International Forum on Strategic Technology, IFOST 2012 [6357628] https://doi.org/10.1109/IFOST.2012.6357628

Analysis of hierarchically-temporal dependencies for handwritten symbols and gestures recognition. / Bolotova, Yulia; Spitsyn, Vladimir.

Proceedings - 2012 7th International Forum on Strategic Technology, IFOST 2012. 2012. 6357628.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Bolotova, Y & Spitsyn, V 2012, Analysis of hierarchically-temporal dependencies for handwritten symbols and gestures recognition. in Proceedings - 2012 7th International Forum on Strategic Technology, IFOST 2012., 6357628, 2012 7th International Forum on Strategic Technology, IFOST 2012, Tomsk, Russian Federation, 18.9.12. https://doi.org/10.1109/IFOST.2012.6357628
Bolotova Y, Spitsyn V. Analysis of hierarchically-temporal dependencies for handwritten symbols and gestures recognition. In Proceedings - 2012 7th International Forum on Strategic Technology, IFOST 2012. 2012. 6357628 https://doi.org/10.1109/IFOST.2012.6357628
Bolotova, Yulia ; Spitsyn, Vladimir. / Analysis of hierarchically-temporal dependencies for handwritten symbols and gestures recognition. Proceedings - 2012 7th International Forum on Strategic Technology, IFOST 2012. 2012.
@inproceedings{8098325f8d6e4507b4dbf1339911e14b,
title = "Analysis of hierarchically-temporal dependencies for handwritten symbols and gestures recognition",
abstract = "This work represents a biologically inspired approach to object recognition based on analysis of hierarchical and temporal data dependencies. The article describes the hierarchical temporal memory model (HTM) and its optimization for object recognition task. Optimization includes Gabor and Canny filter image preprocessing, which makes the model suitable for handwritten symbols and gestures recognition; using of additional clustering on the stage of spatial pooling, a new proposed temporal grouping algorithm increases the overall recognition accuracy of the model; a new genetic algorithm was designed for searching the optimal parameters of the model.",
keywords = "gesture recognition, hierarchical temporal memory, symbols recognition, temporal grouping",
author = "Yulia Bolotova and Vladimir Spitsyn",
year = "2012",
doi = "10.1109/IFOST.2012.6357628",
language = "English",
isbn = "9781467317702",
booktitle = "Proceedings - 2012 7th International Forum on Strategic Technology, IFOST 2012",

}

TY - GEN

T1 - Analysis of hierarchically-temporal dependencies for handwritten symbols and gestures recognition

AU - Bolotova, Yulia

AU - Spitsyn, Vladimir

PY - 2012

Y1 - 2012

N2 - This work represents a biologically inspired approach to object recognition based on analysis of hierarchical and temporal data dependencies. The article describes the hierarchical temporal memory model (HTM) and its optimization for object recognition task. Optimization includes Gabor and Canny filter image preprocessing, which makes the model suitable for handwritten symbols and gestures recognition; using of additional clustering on the stage of spatial pooling, a new proposed temporal grouping algorithm increases the overall recognition accuracy of the model; a new genetic algorithm was designed for searching the optimal parameters of the model.

AB - This work represents a biologically inspired approach to object recognition based on analysis of hierarchical and temporal data dependencies. The article describes the hierarchical temporal memory model (HTM) and its optimization for object recognition task. Optimization includes Gabor and Canny filter image preprocessing, which makes the model suitable for handwritten symbols and gestures recognition; using of additional clustering on the stage of spatial pooling, a new proposed temporal grouping algorithm increases the overall recognition accuracy of the model; a new genetic algorithm was designed for searching the optimal parameters of the model.

KW - gesture recognition

KW - hierarchical temporal memory

KW - symbols recognition

KW - temporal grouping

UR - http://www.scopus.com/inward/record.url?scp=84871823064&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84871823064&partnerID=8YFLogxK

U2 - 10.1109/IFOST.2012.6357628

DO - 10.1109/IFOST.2012.6357628

M3 - Conference contribution

AN - SCOPUS:84871823064

SN - 9781467317702

BT - Proceedings - 2012 7th International Forum on Strategic Technology, IFOST 2012

ER -