Abstract

Based on geometrical facial features and image segmentation, we present a novel algorithm for automatic localization of human eyes in grayscale or color still images with complex background. Firstly, a determination criterion of eye location is established by the prior knowledge of geometrical facial features. Secondly, a range of threshold values that would separate eye blocks from others in a segmented face image (i.e., a binary image) are estimated. Thirdly, with the progressive increase of the threshold by an appropriate step in that range, once two eye blocks appear from the segmented image, they will be detected by the determination criterion of eye location. Finally, the 2D correlation coefficient is used as a symmetry similarity measure to check the factuality of the two detected eyes. To avoid the background interference, skin color segmentation can be applied in order to enhance the accuracy of eye detection. The experimental results demonstrate the high efficiency of the algorithm and correct localization rate.

© 2005 Chinese Optics Letters

Eye center localization and gaze gesture recognition for human–computer interaction

Wenhao Zhang, Melvyn L. Smith, Lyndon N. Smith, and Abdul Farooq
J. Opt. Soc. Am. A 33(3) 314-325 (2016)

Automated segmentation for whole human eye OCT image using RM multistage Mask R-CNN

Xuesong Fu, Jianlin Wang, Zhixiong Hu, Yongqi Guo, and Rutong Wang
Appl. Opt. 60(9) 2518-2529 (2021)

Reconstruction of the point-spread function of the human eye from two double-pass retinal images by phase-retrieval algorithms

Ignacio Iglesias, Norberto López-Gil, and Pablo Artal
J. Opt. Soc. Am. A 15(2) 326-339 (1998)

Moiré pattern movement compensation and quadrature averaging phase retrieval from time series of speckled arbitrary phase shift interferograms for automatic computation of fundus pulsation curve of the human eye

André Malz, Ilos Eix, Wilhelm Stork, and Klaus-Dieter Müller-Glaser
J. Opt. Soc. Am. A 28(5) 934-939 (2011)

Ghost imaging with the human eye

Alessandro Boccolini, Alessandro Fedrizzi, and Daniele Faccio
Opt. Express 27(6) 9258-9265 (2019)