Title :
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
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;
Conference_Titel :
Computational Science and Engineering (CSE), 2014 IEEE 17th International Conference on
Conference_Location :
Chengdu
Print_ISBN :
978-1-4799-7980-6
DOI :
10.1109/CSE.2014.169
