Reliable detection of eye features and eyes in color facial images using ternary eye-verifier

被引:10
作者
Van Huan Nguyen [1 ]
Thi Hai Binh Nguyen [1 ]
Kim, Hakil [2 ]
机构
[1] Inha Univ, Comp Vis Lab, Grad Sch Informat & Commun Engn, 525 Hightech Bldg,253 Yonghyun Dong, Inchon 402751, South Korea
[2] Inha Univ, Sch Informat & Commun Engn, Inchon 402751, South Korea
关键词
Eye verifier; Eye detection; Circular filter; Eye feature extraction; Hybrid face detector; Ternary eye-mask; Ternary eye-template; Eye-weight matrix; IRIS RECOGNITION; FACE DETECTION; ROBUST METHOD; TRACKING;
D O I
10.1016/j.patcog.2012.04.009
中图分类号
TP18 [人工智能理论];
学科分类号
140502 [人工智能];
摘要
Eye detection plays an important role in applications related to face recognition. The position of eyes can be used as a reliable reference for other facial feature detection. This paper presents a novel approach for the precise and reliable detection of eyes by introducing a ternary eye-verifier. Initially, the face region is detected by combining color information and the Haar-like feature detector. The face region is then binarized and filtered with circular filters to detect eye candidates at the peaks in the filtered response. Each eye candidate is fed into a ternary eye-verifier that includes a proposed eye feature extractor based on K-means clustering with compensation for variety in iris color. The eye template in the eye-verifier is constructed based on both the knowledge of eye geometry and the detected eye features. The template matching is made by the ternary Hamming distance. Experiments over a collection of FERET face database and house-made face database with different head poses confirm that the proposed method achieves precise and reliable detection of eyes from color facial images with variation in illumination, pose, eye gazing direction, and race. (C) 2012 Elsevier Ltd. All rights reserved.
引用
收藏
页码:3853 / 3865
页数:13
相关论文
共 47 条
[1]
[Anonymous], 197945 ISOIEC
[2]
[Anonymous], 2007, Journal of Systemics, Cybernetics and Informatics
[3]
[Anonymous], 2005, Computer Vision and Pattern Recognition-Workshops
[4]
[Anonymous], 2008 19 INT C PATT R
[5]
Face and eye detection by CNN algorithms [J].
Balya, D ;
Roska, T .
JOURNAL OF VLSI SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY, 1999, 23 (2-3) :497-511
[6]
Brunelli F.R., 1993, IEEE T PATTERN ANAL, V15, P11
[7]
A robust method for detecting arbitrarily tilted human faces in color images [J].
Chiang, CC ;
Huang, CJ .
PATTERN RECOGNITION LETTERS, 2005, 26 (16) :2518-2536
[8]
How iris recognition works [J].
Daugman, J .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2004, 14 (01) :21-30
[9]
Farkas Leslie G., 1994, P241
[10]
Hamed S.H., 2002, PATTERN RECOGN, V24, P1361