非约束环境下基于小样本的人脸特征精确定位

被引：2

作者：

陈莹 ^{[1
,2
]}

张龙媛 ^{[1
]}

机构：

[1] 江南大学物联网工程学院轻工过程先进控制教育部重点实验室

[2] 上海交通大学系统控制与信息处理教育部重点实验室

来源：

模式识别与人工智能 | 2013年 / 26卷 / 06期

关键词：

非约束环境; 小样本; 人脸特征定位; 高斯混合模型;

D O I：

10.16451/j.cnki.issn1003-6059.2013.06.005

中图分类号：

TP391.41 [];

学科分类号：

080203 ;

摘要：

针对非约束环境下的人脸特征定位问题,在概率框架下提出一种基于小样本的精确定位策略.通过对比分析,提取人脸主要特征的颜色和灰度信息及人脸特征之间的几何约束信息,利用混合高斯模型分别对其进行概率建模.之后建立定位融合策略,不仅考虑每种人脸特征的概率分布,还考虑其周围元素的概率分布特性,及各元素之间的几何约束.实验结果表明,该方法能在少量训练样本图像且样本个体较为单一的条件下,实现人脸主要特征的精确定位,且定位精度高于现有方法.

引用

页码：577 / 583

页数：7

共 14 条

[1] Regression and Classification Approaches to Eye Localization in Face Images. Everingham M,Zisserman A. Proc of the7th International Conference on Automatic Face and Gesture Recognition . 2006
[2] Face Detection in Color Images. Rein-Lien Hsu,Mohamed Abdel-Mottaleb,Anil K Jain. IEEE Transactions on Pattern Analysis and Machine Intelligence . 2002
[3] Discovery of collocation patterns:from visual words to visual phrases. Yuan J,Wu Y,Yang M. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . 2007
[4] A Generative Framework for Real Time Object Detection and Classification. Fortenberry B,Movellan J. Computer Vision and Image Understanding . 2005
[5] Robust Precise Eye Location under Probabilistic Framework. Ma Yong,Ding Xiaoqing,Wang Zhenger,et al. Proc of the6th IEEE International Conference on Automatic Face and Gesture Recog-nition . 2004
[6] Adjusted Pixel Features for Ro-bust Facial Component Classification. Mayer C,Wimmer M,Radig B. Image and Vision Compu-ting . 2010
[7] A Comparison of Face and Facial Feature Detectors Based on the Viola-Jones General Object Detection Framework. Castrillón M,Déniz O,Hernández D,et al. Machine Vision and Applications . 2011
[8] 2D Cascaded AdaBoost for Eye Localization. Niu Zhiheng,Shan Shiguang,Yan Shengye,et al. Proc of the18th International Conference on Pattern Recognition . 2006
[9] Robust Real Time Object Detection. Viola P,Jones M. research microsoft.com/en-us/um/people/viola/Pubs/Detect/ViolaJones_IJCV.pdf . 2001
[10] "Multi-view face and eye detection using discriminant features.". Peng Wang,Qiang Ji. Computer Vision and Image Understanding . 2007

← 1 2 →