Proceedings of the International Seminar on Computation, Communication and Control

Eye Location Method based on gray projection with improved skin color segmentation

Authors
Feng KaiPing, Yang Pan
Corresponding Author
Feng KaiPing
Available Online March 2015.
DOI
10.2991/is3c-15.2015.7How to use a DOI?
Keywords
eye location; skin color segmentation; otsu
Abstract

The accuracy of eye location using gray projection method is dependent on the quality of the ambient light, the face posture and facial hair in front of the face . in order to solve the actual environment problem, this paper proposes a improved color segmentation and repeatedly reused gray projection which perform four times gray projection in face area.The experiments show this detection method can be used to avoid the disturb of actual environment and it can be up to 20 frames per second or more.This method can detected different human faces in different poses, the accuracy and efficiency of this algorithm has high robustness.

Copyright
© 2015, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

Volume Title
Proceedings of the International Seminar on Computation, Communication and Control
Series
Advances in Computer Science Research
Publication Date
March 2015
ISBN
978-94-62520-55-4
ISSN
2352-538X
DOI
10.2991/is3c-15.2015.7How to use a DOI?
Copyright
© 2015, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Cite this article

TY  - CONF
AU  - Feng KaiPing
AU  - Yang Pan
PY  - 2015/03
DA  - 2015/03
TI  - Eye Location Method based on gray projection with improved skin color segmentation
BT  - Proceedings of the International Seminar on Computation, Communication and Control
PB  - Atlantis Press
SP  - 29
EP  - 32
SN  - 2352-538X
UR  - https://doi.org/10.2991/is3c-15.2015.7
DO  - 10.2991/is3c-15.2015.7
ID  - KaiPing2015/03
ER  -