一种改进的基于主动形状模型的人脸特征定位方法  

A Improved Facial Feature Localization Method Based On Active Shape Model

作　　者：田建华[1] 

机构地区：[1]菏泽学院远程教育学院,山东菏泽274000

出　　处：《菏泽学院学报》2011年第2期43-47,共5页Journal of Heze University

摘　　要：主动形状模型是目前一种常用的人脸特征定位方法.针对传统的主动形状模型过度依赖模型初始参数的设置问题,提出了一种改进的基于主动形状模型的人脸特征定位方法.首先,通过样本学习得到输入新图像的灰度重构系数,并将这组系数用于人脸形状的重构,再由重构出的人脸形状得到主动形状模型的初始参数,然后通过不断调整模型参数减少模型与目标轮廓的距离误差,最后在数次迭代后达到模型与实际人脸特征轮廓的匹配.与基于传统主动形状模型的特征定位相比,改进的主动形状模型具有较高的准确性,能快速定位出各目标特征.Active Shape Model is one of the mostly used methods for facial feature locating.Regarding the traditional ASM excessively depend on the setting of the initial parameter of the model,a facial feature locating method was presented based on improved ASM.Firstly,obtain the reconstruction parameters of the new gray image by example-based learning and use it to reconstruction the shape of the new image and compute the initial parameters of the ASM by the reconstructed facial shape.Then reduce the distance error between the model and the target contour by adjusting the parameters of the model.Finally,the model is matched with the facial feature profile after several iterations.In contrast with the method of facial feature locating based on conventional ASM,the improved ASM has higher veracity and locates the object feature rapidly.

关 键 词：人脸特征定位 样本学习 主动形状模型 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]