基于圆形滑动窗口的瞳孔定位算法
DOI:
CSTR:
作者:
作者单位:

上海理工大学光电信息与计算机工程学院 上海 200082

作者简介:

通讯作者:

中图分类号:

TN911.73

基金项目:


Pupil location algorithm based on circular sliding window
Author:
Affiliation:

School of optoelectronic information and computer engineering, Shanghai University of Technology, Shanghai 200082, China

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    瞳孔定位是眼动识别中的一个关键步骤。针对目前瞳孔定位算法存在精度低、耗时高、人脸偏转时的定位误差较大等问题,本文提出了一种通过创建滑动窗口来精确定位瞳孔中心的算法。首先利用CLM模型提取人脸的眼部区域,对提取后的图片进行预处理,然后通过创建圆形滑动窗口对图片进行扫描并计算每个窗口内灰度值的和,利用人眼瞳孔的灰度值相对较低这一特性选取灰度值相对较低的窗口为人眼瞳孔区域,计算出其中心点坐标即可定位出瞳孔中心。实验结果表明,该算法针对不同测试对象可以相对精确地定位瞳孔中心,并且具有较高的鲁棒性。

    Abstract:

    pupil localization is a key step in pupil recognition. In order to solve the problems of low accuracy, missing detection and false detection in the current pupil location algorithm, this paper proposes an algorithm to accurately locate the pupil center by creating a sliding window. Firstly, CLM model is used to extract the eye region of human face, and the extracted image is preprocessed. Then, by creating a circular sliding window to scan the image and calculate the sum of the gray values of pixels in each window. Taking advantage of the fact that the gray value of the pupil is very low, the window with the lowest gray value is selected as the pupil region, and the coordinates of its center point are calculated as the coordinates of the pupil center. The experimental results show that the algorithm can accurately locate the pupil center for different test objects, and can enhance the robustness of the system.

    参考文献
    相似文献
    引证文献
引用本文

童言,穆平安,林玉莹.基于圆形滑动窗口的瞳孔定位算法[J].电子测量技术,2021,44(2):99-103

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2024-12-19
  • 出版日期:
文章二维码
×
《电子测量技术》
财务封账不开票通知