The Real-Time Eye Detection for Single User Based on Template Matching

Author

Weijia Zhong ; Ziqiang Huang

Author_Institution

Res. Inst. Electron. Sci. & Technol., Univ. of Electron. Sci. & Technol. of China, Chengdu, China

fYear

2014

fDate

19-21 Dec. 2014

Firstpage

831

Lastpage

834

Abstract

A novel eye detection method based on template matching is proposed for glasses-free 3D device. Before matching, get the average eye template through a great quantity of eye images, splice several average templates into a chessboard template. Then locate the position of eyes by calculating the correlation coefficient between template and the candidate image. It has been testified that these algorithm simplify the calculation, ensure the accuracy and improve the efficiency. Moreover, these method provide an idea that implementing the algorithm through hardware circuit.

Keywords

image matching; object detection; chessboard template; correlation coefficient; eye image; eye template; glasses-free 3D device; hardware circuit; realtime eye detection; template matching; Accuracy; Algorithm design and analysis; Correlation coefficient; Educational institutions; Error analysis; Hardware; Three-dimensional displays; Chessboard template; Eye detection; Template matching; Threshold selection;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Science and Engineering (CSE), 2014 IEEE 17th International Conference on

Conference_Location

Chengdu

Print_ISBN

978-1-4799-7980-6

Type

conf

DOI

10.1109/CSE.2014.169

Filename

7023679