Skip to main navigation Skip to search Skip to main content

Real-time hand posture recognition using Haar-like and topological feature

  • Cao Chuqing*
  • , Ruifeng Li
  • *Corresponding author for this work
  • School of Mechatronics Engineering, Harbin Institute of Technology

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

Abstract

A new method based on Haar-like and topological feature is proposed for hand posture recognition. Initially, the region of the hand is detected by a statistical method based on Haar-like features and color segmentation technique. With this method, a group of hand posture regions can be detected in real time with high recognition accuracy. Then, the topology is applied on the detected regions so as to classify the different postures. Applying this method to human-robot interaction, experimental results show that our method achieves satisfactory performance.

Original languageEnglish
Title of host publication2010 International Conference on Machine Vision and Human-Machine Interface, MVHI 2010
Pages683-687
Number of pages5
DOIs
StatePublished - 2010
Externally publishedYes
Event2010 International Conference on Machine Vision and Human-Machine Interface, MVHI 2010 - Kaifeng, China
Duration: 24 Apr 201025 Apr 2010

Publication series

Name2010 International Conference on Machine Vision and Human-Machine Interface, MVHI 2010

Conference

Conference2010 International Conference on Machine Vision and Human-Machine Interface, MVHI 2010
Country/TerritoryChina
CityKaifeng
Period24/04/1025/04/10

Keywords

  • Haar-like feature
  • Human-robot interaction
  • Image segmentation
  • Posture recognition

Fingerprint

Dive into the research topics of 'Real-time hand posture recognition using Haar-like and topological feature'. Together they form a unique fingerprint.

Cite this