Detection of eye locations in unconstrained visual images

Abstract

This paper describes a computational approach for accurately determining the location of human eyes in unconstrained monoscopic gray level images. The proposed method is based on exploiting the flow field characteristics that arise due to the presence of a dark iris surrounded by a light sclera. A novel aspect of the proposed method lies in its use of both spatial and temporal information to detect the location of the eyes. The spatial processing utilizes flow field information to select a pool of potential candidate locations for the eyes. Temporal processing uses the principle of continuity to filter out the actual location of the eyes from the pool of potential candidates. Extensions for gaze angle determination, and the tracking of human point-of-regard are indicated.

Communication via eye blinks and eyebrow raises: video-based human-computer interfaces

“…Methods for detecting the eyes include the use of gradient flow fields [37], color-based techniques for detection of the eye sclera [5], horizontal gradient maps of a skin-colored region [48,51], and pupil detection using infrared or other special lighting [2,31,40,54]. References [1,7,13,17,18,21,38,40,50] explain various face and head tracking techniques previously employed.…”

Minimal Neighborhood Mean Projection Function and Its Application to Eye Location

“…的意义.除了投影之外,还有许多有效的眼睛定位方法,如图像梯度法 [6] 、Hough 变换法 [7] 、模板匹配法 [8] 、区域 增长法 [9] 等.而若干种方法的结合往往能给出令人满意的定位效果.Xu 和 Shi [10] 利用积分投影给出眼睛位置的 初始估计,再用加权 Hough 变换进行细定位.Du [11] 则是采用谷检测算法和人脸对称性获得初始估计,然后,采用 缺 失 估 计 (lacunarity estimation) 进 行 筛 选 . 小 波 作 为 一 种 图 像 特 征 提 取 方 法 也 被 用 于 眼 睛 定 位 .Huang 和 Wechsler [12] 利用最优小波包提取眼睛特征,并利用径向基函数分类眼睛与非眼睛区域.Feris [13] 等人采用两层 Gabor 小波神经网络来完成人脸粗定位和眼睛精确定位的工作.Gabor 小波还被用来处理眼睛定位中光照变化 的问题 [14] .还有一些学者将眼睛定位看作是一个典型的模式分类问题,即区分眼睛和非眼睛区域.一些模式分类 的方法,如 Boosting,SVM 等,也被用于眼睛定位 [15−18] .关于此类方法的介绍和对比,参见文献 [19].…”

Face Verification in Polar Frequency Domain: A Biologically Motivated Approach

“…This face detection stage was implemented using a cascade of classifiers algorithm for the face detection [17] followed by an Active Appearance Model algorithm (AAM) [18] for the detection of the eyes region. Within this region, we used flow field information [19] to determine the eye center. Approximately 1% of the faces were not localized by the AAM algorithm, in which cases the eyes regions coordinates were set to a fix value derived from the mean of the other faces.…”