Integrating LCS and SVM for 3D handwriting recognition on handheld devices using accelerometers

Wang Hsin Hsu, Yi Yuan Chiang, Wen Yen Lin, Wei Chen Tai, Jung Shyr Wu

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

2 Scopus citations

Abstract

Based on accelerometer, we propose a 3D handwriting recognition system in this paper. The system is consists of 4 main parts: (1) data collection: a single tri-axis accelerometer is mounted on a handheld device to collect different handwriting data. A set of key patterns have to be written using the handheld device several times for consequential processing and training. (2) data preprocessing: time series are mapped into eight octant of three-dimensional Euclidean coordinate system. (3) data training: LCS and SVM are combined to perform the classification task. (4) pattern recognition: using the trained SVM model to carry out the prediction task. To evaluate the performance of our handwriting recognition model, we choose the experiment of recognizing a set of English words. The accuracy of classification could be achieved at about 93%.

Original languageEnglish
Title of host publicationProceedings of the 3rd International Conference on Communications and Information Technology, CIT'09
Pages195-197
Number of pages3
StatePublished - 2009
Event3rd International Conference on Communications and Information Technology, CIT'09 - Athens, Greece
Duration: 29 Dec 200931 Dec 2009

Publication series

NameProceedings of the 3rd International Conference on Communications and Information Technology, CIT'09

Conference

Conference3rd International Conference on Communications and Information Technology, CIT'09
Country/TerritoryGreece
CityAthens
Period29/12/0931/12/09

Keywords

  • Accelerometer
  • Gesture recognition
  • Handwriting recognition
  • LCS
  • SVM

Fingerprint

Dive into the research topics of 'Integrating LCS and SVM for 3D handwriting recognition on handheld devices using accelerometers'. Together they form a unique fingerprint.

Cite this