一种改进的基于随机森林的快速人眼定位方法

马越; 贺光辉

Chinese

您当前的位置：

首页 >

文章列表页 >

一种改进的基于随机森林的快速人眼定位方法

更新时间：2026-09-04

- 一种改进的基于随机森林的快速人眼定位方法
- A Revised Eye-Localization Algorithm Based on Random Forest
- 微电子学与计算机 2016年33卷第7期页码：1-4
- 作者机构：
  
  上海交通大学, 微电子学院,上海,200240
- 作者简介：
- 基金信息：
  
  国家自然科学基金项目 61306026
- DOI：
  中图分类号：
- 纸质出版：2016
- 稿件说明：
移动端阅览
马越, 贺光辉. 一种改进的基于随机森林的快速人眼定位方法[J]. 微电子学与计算机, 2016, 33(7): 1-4, 10.

MA Yue, HE Guang-hui. A Revised Eye-Localization Algorithm Based on Random Forest[J]. 2016, 33(7): 1-4.
马越, 贺光辉. 一种改进的基于随机森林的快速人眼定位方法[J]. 微电子学与计算机, 2016, 33(7): 1-4, 10. DOI：

MA Yue, HE Guang-hui. A Revised Eye-Localization Algorithm Based on Random Forest[J]. 2016, 33(7): 1-4. DOI：

摘要

为了得到更强的鲁棒性和更好的实时性

针对精确的人眼定位提出了基于随机森林的自适应梯度提升算法(Adaptive Gradient Boosting Random Forest)

同时引入了更加多样的训练样本来降低诸如光线强弱

旋转角度等外部环境对定位的影响.在BioID数据库中

此方法的准确率为92%

定位时间少于1 ms.实验结果表明

它已经满足在大多数不可控环境对鲁棒性和实时性的要求.

Abstract

In this paper

we present an enhanced Random Forest(RF) model for precise eye localization. To extend Random Forest

we 1) propose the randomized trees with adaptive gradient boosting for a more accurate eye localization 2) introduce a series of standard samples with random perturbation for the robustness to changes in illumination and head pose and eye rotation. Performance results of our methods showed that it can obtain an accuracy of 92 percent on BioID database and gives a frame processing time of less than 1ms because of the low computation cost. Experimental results on the challenging BioID database show that our model can locate eyes accurately and efficiently under a broad range of uncontrolled variations involving lightings

camera qualities

occlusions

etc.

关键词

Keywords

references

Valenti R, Sebe N, Gevers T. Combining head pose and eye location information for gaze estimation[J]. Image Processing, IEEE Transactions on, 2012, 21(2): 802-815. DOI: 802

MarkuŠ N. Eye pupil localization with an ensemble of randomized trees[J]. Pattern recognition, 2014, 47(2): 578-587. DOI: 578

Valenti R, Gevers T. Accurate eye center location and tracking using isophote curvature[C]//Computer Vision and Pattern Recognition, CVPR 2008. IEEE Conference on. USA, Alaska, 2008: 1-8.

Kroon B, Hanjalic A, Maas S M. Eye localization for face matching: is it always useful and under what conditions[C]//Proceedings of the 2008 international conference on Content-based image and video retrieval. Canada, Niagara Falls, 2008: 379-388.

Yi D, Lei Z, Li S Z. A robust eye localization method for low quality face images[C]//Biometrics (IJCB), 2011 International Joint Conference on. USA, Washington DC, 2011: 1-6.

Tan X. Enhanced pictorial structures for precise eye localization under incontrolled conditions[C]//Computer Vision and Pattern Recognition, 2009. CVPR 2009. USA, Florida, Miami, IEEE Conference on, 2009: 1621-1628.

Fasel I, Fortenberry B, Movellan J. A generative framework for real time object detection and classification[J]. Computer Vision and Image Understanding, 2005, 98(1): 182-210. DOI: 182

Asadifard M, Shanbezadeh J. Automatic adaptive center of pupil detection using face detection and cdf analysis[C]//Proceedings of the International MultiConference of Engineers and Computer Scientists. China, Hongkong, 2010: 3-5.

Valenti R, Gevers T. Accurate eye center location and tracking using isophote curvature[C]//Computer Vision and Pattern Recognition, CVPR 2008. IEEE Conference on. USA, Anchorage, Alaska, 2008.

Peng K. A robust agorithm for eye detection on gray intensity face without spectacles[J]. Journal of Computer Science % Technology, 2005, 5(3): 127-133. DOI: 127

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

一种用于极低压boost系统的高效率电荷泵

基于改进RT-DETR的航拍小目标检测算法

一种基于特征上下文理解与切片分析的肺结核检测算法

基于多尺度融合与小目标增强的航拍车辆检测算法

基于区块链的AI生成内容溯源框架设计研究