Hand gesture recognition for man-machine interaction

Author

Kapuscinski, Tomasz ; Wysocki, Marian

Author_Institution

Rzeszow Univ. of Technol., Poland

fYear

2001

fDate

2001

Firstpage

91

Lastpage

96

Abstract

Addresses some basic problems of hand gesture recognition. Three steps important in building gestural vision-based interfaces are discussed. The first step is the hand location through detection of skin colored regions. Representative methods based on 2D color histograms are described and compared. The next step is the hand shape (posture) recognition. An approach that uses the morphological hit-miss operation is presented. Finally, application of hidden Markov models in recognition of dynamic gestures is explained. An experimental system that uses the discussed methods in real time is described and recognition results are presented

Keywords

Bayes methods; gesture recognition; hidden Markov models; image colour analysis; image segmentation; image sequences; mathematical morphology; 2D color histograms; dynamic gestures; gestural vision-based interfaces; hand gesture recognition; hand location; hand shape recognition; hidden Markov models; man-machine interaction; morphological hit-miss operation; posture recognition; skin colored regions; Application software; Computer science; Hidden Markov models; Histograms; Human robot interaction; Image sequences; Paper technology; Robustness; Shape; Skin;

fLanguage

English

Publisher

ieee

Conference_Titel

Robot Motion and Control, 2001 Proceedings of the Second International Workshop on

Conference_Location

Bukowy Dworek

Print_ISBN

83-7143-515-0

Type

conf

DOI

10.1109/ROMOCO.2001.973437

Filename

973437