A New Skin Color Tracking Method Using an Oscillatory Neural Network Model for Moving Pictures

Title
A New Skin Color Tracking Method Using an Oscillatory Neural Network Model for Moving Pictures
Authors
황용원오상록유범재이지용정문호박민용
Keywords
Face Tracking; Skin color detection; oscillatory correlation; LEGION
Issue Date
2010-11
Publisher
The 7th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI 2010)
Citation
, 200-203
Abstract
This paper proposes a real-time face detection and tracking system that uses neural oscillators which can be applied to access regulation system or control systems of user authentication as well as a new algorithm. The system that is suggested in this paper can broadly be broken into two stages of process. The first stage is the process of face extraction, which involves the acquisition of real-time RGB24bit color video delivering with the use of a cheap webcam. Face detection method using LEGION algorithm. Skin color is extracted by changing into color model on the basis of YCrCb and through the process operating segmentation to the extracted skin color area, face area is extracted as well. The second stage is a method for face tracking by discovering the leader neuron that has the greatest connection strength amongst neighbor neurons of extracted face area. Along with the suggested method, the necessary elements of face tracking, stability as well as scale problems could be resolved.
URI
http://pubs.kist.re.kr/handle/201004/39121
Appears in Collections:
KIST Publication > Conference Paper
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE