人脸老化模拟与PCA算法结合的人脸识别模型  

A Model of Face Recognition Based on Feature Location and PCA Algorithm to Reduce the Interference of Age Factors

作　　者：余丰江 张波[1] 贾宝林 Yu Feng-jiang;Zhang Bo;Jia Bao-lin(School of Business,Southwest University,Chongqing Rongchang 402460)

机构地区：[1]西南大学商贸学院

出　　处：《电子质量》2019年第6期79-86,共8页Electronics Quality

摘　　要：针对如何在读取两张年龄有较大跨度的人物面部照片的情况下来进行人脸识别这个问题,该文给出了较有创新性的方法。首先使用高斯模型,肤色信息人脸检测的分割算法,迭代算法提取人脸特征部位。然后使用基于人脸外轮廓的局部曲率标准差的个性化脸型匹配算法结合关于形状和颜色的衰老合成模型和年龄原型的纹理增强合成模型给出了基于个性化原型的人脸老化图像合成方法。接着在传统PCA算法的基础上给出了结合人脸老化模拟的改进型算法思路,从人脸不易变量和易变量的重建两方面入手判定人脸的相似性,理论上可以较为准确地在跨年龄情况下进行人脸识别。In order to solve the problem of how to read two large-span facial photos of people,this paper presents a more innovative method.Firstly,we use Gauss model,skin color information face detection segmentation algorithm, and iterative algorithm to extract face feature parts.Then,a personalized face pattern matching algorithm based on local curvature standard deviation of face contour is used to synthesize the aging image based on personalized prototype,which combines the aging synthesis model of shape and color and the texture enhancement synthesis model of age prototype.Then,on the basis of the traditional PCA algorithm,an improved algorithm combined with face aging simulation is proposed.The similarity of face can be judged from two aspects: the reconstruction of face variables and the reconstruction of face variables.In theory,face recognition can be carried out more accurately in cross-age situations.

关 键 词：个性化脸型匹配算法 年龄纹理 衰老合成模型 改进的PCA算法 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]