Atlantis Press Paper Details: Finding The Finger By The Boundary Vector Product

A finger finding procedure has been presented to recognize the finger number of the hand gesture. The hand gesture is extracted from the stationary background and transformed into a binary image. The hue attribute, that is, the I value in the YIQ color space is used to extract the hand gesture shape. This attribute is not so sensitive to the light change and the other noises while catching the image frames. The binary image of the hand gesture shape is processed with erosion several times to eliminate the noises and then processed with dilation several times to recover the original shape. After the removal of the image noises, a boundary detection algorithm is used to trace the border of the hand shape from the binary image. The border of the hand shape can be used to calculate the vector product along the boundary. From the vector product along the boundary, the finger number of the hand gesture can be obtained.

		back to author index

title:		Finding The Finger By The Boundary Vector Product
publication:		JCIS-2006 Proceedings
part of series:		Advances in Intelligent Systems Research
ISBN:		978-90-78677-01-7
ISSN:		1951-6851
DOI:		doi:10.2991/jcis.2006.261 (how to use a DOI)
author(s):		Yuan-Fei Cheng
corresponding author:		Yuan-Fei Cheng
publication date:		October 2006
keywords:		finger calculation, hand gesture, boundary detection, vector product
abstract:		A finger finding procedure has been presented to recognize the finger number of the hand gesture. The hand gesture is extracted from the stationary background and transformed into a binary image. The hue attribute, that is, the I value in the YIQ color space is used to extract the hand gesture shape. This attribute is not so sensitive to the light change and the other noises while catching the image frames. The binary image of the hand gesture shape is processed with erosion several times to eliminate the noises and then processed with dilation several times to recover the original shape. After the removal of the image noises, a boundary detection algorithm is used to trace the border of the hand shape from the binary image. The border of the hand shape can be used to calculate the vector product along the boundary. From the vector product along the boundary, the finger number of the hand gesture can be obtained.
copyright:		© Atlantis Press. This article is distributed under the terms of the Creative Commons Attribution License, which permits non-commercial use, distribution and reproduction in any medium, provided the original work is properly cited.
full text:		JCIS06-CVPRIP-29.pdf (117 K)