A novel recognition system for digits writing in the air using coordinated path ordering

Chiang Wang*, Chung Yen Su, Chun Lin Lin

*Corresponding author for this work

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

5 Citations (Scopus)

Abstract

With the invention of Microsoft Kinect sensor, human-computer interaction is gaining its attention and becoming available for widespread use. The previous study presented a method of Kinect-based mid-air handwritten digit recognition for Android smart phones with a recognition accuracy of only about 94.6%. In this paper, we propose an improved method based on the normalizing and scaling of path order coordinates. With that, the proposed method leads to accuracy elevation and executing time reduction. Experimental results show an average recognition accuracy rate of 96.8% was achieved for each number.

Original languageEnglish
Title of host publicationICIIBMS 2015 - International Conference on Intelligent Informatics and Biomedical Sciences
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages244-249
Number of pages6
ISBN (Electronic)9781479985623
DOIs
Publication statusPublished - 2016 Mar 22
EventInternational Conference on Intelligent Informatics and Biomedical Sciences, ICIIBMS 2015 - Okinawa, Japan
Duration: 2015 Nov 282015 Nov 30

Publication series

NameICIIBMS 2015 - International Conference on Intelligent Informatics and Biomedical Sciences

Other

OtherInternational Conference on Intelligent Informatics and Biomedical Sciences, ICIIBMS 2015
Country/TerritoryJapan
CityOkinawa
Period2015/11/282015/11/30

Keywords

  • Kinect sensor
  • accuracy rate
  • handwritten digit recognition
  • human-computer interaction
  • support vector machine

ASJC Scopus subject areas

  • Signal Processing
  • Health Informatics
  • Biotechnology
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'A novel recognition system for digits writing in the air using coordinated path ordering'. Together they form a unique fingerprint.

Cite this