基于肤色模型和高斯分布的多人脸检测方法  

Multi-face Detection Method Based on Skin-color Model and Gaussian Distribution

作　　者：刘在英[1] 杨平[1] 张丽晓[1] 

机构地区：[1]上海杉达学院信息科学与技术学院,上海201209

出　　处：《计算机与现代化》2013年第10期30-34,共5页Computer and Modernization

基　　金：上海市教育委员会科研创新项目(11YZ282);上海市民办高校骨干教师科研项目(Z-2204-11-018)

摘　　要：针对由于背景复杂、肤色、表情等给人脸检测带来的困难,提出一种改进的基于肤色模型和高斯分布多人脸检测方法。该方法利用肤色模型获取肤色区域,通过多种人脸显性特征得到人脸候选区域和对边缘检测后二值图像分别向X,Y轴投影,建立高斯分布模型来准确定位人脸的区域。实验结果表明,该算法检测速度快、定位率高、鲁棒性强。Focusing on multi-face detection problems of color image with complicated background and so on, this paper proposes an improved multi-face detection method based on skin-color model and Gaussian distribution. Skin regions are acquired using skin-color model in the first stage. In the second stage, facial features are utilized to obtain face candidates. Finally, two Gaussi- an curves are acquired by projecting the edge-detection-image to X-axes and Y-axes respectively, and an accurate face region is found through the solution of Gaussian equation. Simulation shows that the robust method proposed in the paper can improve the multi-face detection accuracy and the detection speed.

关 键 词：人脸检测 人脸特征提取 高斯分布模型 投影 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]