Eye feature points detection by CNN with strict geometric constraint

Chunning Meng; Xuepeng Zhao; Mingkui Feng; Shengjiang Chang

doi:10.1117/12.2245167

29 August 2016 Eye feature points detection by CNN with strict geometric constraint

Chunning Meng, Xuepeng Zhao, Mingkui Feng, Shengjiang Chang

Author Affiliations +

Proceedings Volume 10033, Eighth International Conference on Digital Image Processing (ICDIP 2016); 1003340 (2016) https://doi.org/10.1117/12.2245167
Event: Eighth International Conference on Digital Image Processing (ICDIP 2016), 2016, Chengu, China

Abstract

The detection accuracy of facial landmarks or eye feature points is influenced by geometric constraint between the points. However, this constraint is far from being research in existing convolutional neural network (CNN) based points detection. Whether strict geometric constraint can improve the performance is not studied yet. In this paper, we propose a new approach to estimate the eye feature points by using single CNN. A deep network containing three convolutional layers is built for points detection. To analyze the influence of geometric constraint on CNN based points detection, three definitions of the eye feature points are proposed and used for calibration. The experiments show that excellent performance is achieved by our method, which prove the importance of the strict geometric constraint in points detection based on CNN. In addition, the proposed method achieves high accuracy of 96.0% at 5% detection error, but need less computing time than the cascade structure.

Citation Download Citation

Chunning Meng, Xuepeng Zhao, Mingkui Feng, and Shengjiang Chang "Eye feature points detection by CNN with strict geometric constraint", Proc. SPIE 10033, Eighth International Conference on Digital Image Processing (ICDIP 2016), 1003340 (29 August 2016); https://doi.org/10.1117/12.2245167

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE