基于Mean-BIF的跨年龄人脸识别
首发时间:2017-09-25
摘要:近年来,跨年龄人脸识别受到越来越广泛的关注。除了基因,人脸老化过程还受到生活方式等多种因素的影响。本文采用BIF和KR-RCA实现跨年龄人脸识别。首先对人脸图像进行旋转、对齐、剪切等归一化处理,然后对处理好的图像提取Mean-BIF特征,最后采用KR-RCA进行分类。经过在FG-NET和MORPG两个数据库上实验证明,本文提出的方法可以有效地实现跨年龄人脸识别。
For information in English, please click here
Cross-Age Face Recognition based on Biologically-Inspired Feature
Abstract:Recent years,Age-invariant face recognitionhas received increasing attention in the face recognition community due to its great help for government application(e.g. passport verification). Inaddition to biological factors,face aging processing is affacted by many factors (e.g. lifestyle). In this paper, biologically-inspired feature and kernel regularized relevant component analysis are used for age-invariant face recognition. Firstly, the mug shot is preprocessed with rotation, alignment and cropping. Then, biologically-inspired feature(BIF)with mean pooling is extractedform the face image after preprocessing. At last, kernel regularized relevant component analysis(KR-RCA) is used to get the final identification. Experimental results on FG-NET and MORPH datasets, which are most widely used in face aging problems, are presented to show the efficiency of proposed method.
Keywords: Pattern recognition Biologically-inspired feature KR-RCA Age Face recognition
基金:
引用
No.****
动态公开评议
共计0人参与
勘误表
基于Mean-BIF的跨年龄人脸识别
评论
全部评论0/1000