Summary: In Proceedings of the IEEE CVPR, pp. 892­897, Santa Barbara, 1998
Extraction and Classification of Visual Motion Patterns for
Hand Gesture Recognition
Ming­Hsuan Yang and Narendra Ahuja
Beckman Institute and Department of Electrical and Computer Engineering
University of Illinois at Urbana­Champaign
Urbana, IL 61801
Abstract
We present a new method for extracting and clas­
sifying motion patterns to recognize hand gestures.
First, motion segmentation of the image sequence is
generated based on a multiscale transform and at­
tributed graph matching of regions across frames. This
produces region correspondences and their affine trans­
formations. Second, color information of motion re­
gions is used to determine skin regions. Third, hu­
man head and palm regions are identified based on
the shape and size of skin areas in motion. Finally,
affine transformations defining a region's motion be­
tween successive frames are concatenated to construct

Source: Ahuja, Narendra - Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign

Collections: Computer Technologies and Information Sciences; Engineering