Face as mouse through visual face tracking

Jilin Tu, T. Huang, Hai Tao

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


This paper introduces a novel camera mouse driven by 3D model based visual face tracking technique. While camera becomes standard configuration for personal computer (PC) and computer speed becomes faster and faster, achieving human machine interaction through visual face tracking becomes a feasible solution to hand-free control. The human facial movement can be decomposed into rigid movement, e.g. rotation and translation, and non-rigid movement, such as the open/close of mouth, eyes, and facial expressions, etc. We introduce our visual face tracking system that can robustly and accurately retrieve these motion parameters from video at real-time. After calibration, the retrieved head orientation and translation can be employed to navigate the mouse cursor, and the detection of mouth movement can be utilized to trigger mouse events. 3 mouse control modes are investigated and compared. Experiments in Windows XP environment verify the convenience of navigation and operations using our face mouse. This technique can be an alternative input device for people with hand and speech disability and for futuristic vision-based game and interface.

Original languageEnglish (US)
Title of host publicationProceedings - 2nd Canadian Conference on Computer and Robot Vision, CRV 2005
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages8
ISBN (Electronic)0769523196, 9780769523194
StatePublished - 2005
Externally publishedYes
Event2nd Canadian Conference on Computer and Robot Vision, CRV 2005 - Victoria, Canada
Duration: May 9 2005May 11 2005

Publication series

NameProceedings - 2nd Canadian Conference on Computer and Robot Vision, CRV 2005


Other2nd Canadian Conference on Computer and Robot Vision, CRV 2005

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Software


Dive into the research topics of 'Face as mouse through visual face tracking'. Together they form a unique fingerprint.

Cite this