Illumination-invariant hand gesture recognition

América Ivone Mendoza-Morales; Daniel Miramontes-Jaramillo; Vitaly Kober

doi:10.1117/12.2186696

9 September 2015 Illumination-invariant hand gesture recognition

América Ivone Mendoza-Morales, Daniel Miramontes-Jaramillo, Vitaly Kober

Proceedings Volume 9598, Optics and Photonics for Information Processing IX; 95980W (2015) https://doi.org/10.1117/12.2186696
Event: SPIE Optical Engineering + Applications, 2015, San Diego, California, United States

Abstract

In recent years, human-computer interaction (HCI) has received a lot of interest in industry and science because it provides new ways to interact with modern devices through voice, body, and facial/hand gestures. The application range of the HCI is from easy control of home appliances to entertainment. Hand gesture recognition is a particularly interesting problem because the shape and movement of hands usually are complex and flexible to be able to codify many different signs. In this work we propose a three step algorithm: first, detection of hands in the current frame is carried out; second, hand tracking across the video sequence is performed; finally, robust recognition of gestures across subsequent frames is made. Recognition rate highly depends on non-uniform illumination of the scene and occlusion of hands. In order to overcome these issues we use two Microsoft Kinect devices utilizing combined information from RGB and infrared sensors. The algorithm performance is tested in terms of recognition rate and processing time.

Citation Download Citation

América Ivone Mendoza-Morales, Daniel Miramontes-Jaramillo, and Vitaly Kober "Illumination-invariant hand gesture recognition", Proc. SPIE 9598, Optics and Photonics for Information Processing IX, 95980W (9 September 2015); https://doi.org/10.1117/12.2186696

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available