基于ICA系数稀疏表示的年龄自动估计
摘 要
基于人脸图像的人类生理年龄自动估计是人脸识别领域的一个重要研究方向。对此,使用一种基于WTA(winner-take-all)竞争规则的独立分量分析方法来实现年龄估计任务。首先对人脸图像进行归一化处理,利用PCA方法进行白化预处理以进一步降低训练集合的维数;然后,使用WTA-ICA稀疏表示实现人脸图像的特征提取。最后在FG-NET Aging database人脸数据库的实验结果表明,该算法对基于人脸图像的年龄估计获得了较好的结果。
关键词
Age Automation Estimation Based on A ICA Coefficient Sparse Description Algorithm
() Abstract
Automatic age estimation based on facial images is an important research trend of face recognition. Here we proposed an independent component analysis method based on winner-take-all(WTA)rule to realize the age estimation task. Firstly, applying the PCA method to reduce the dimensions of original training data; then, using the proposed WTA-ICA coefficient sparse description method to extract the feature.Finally, the experimental results on the FG-NET Aging database indicate that the proposed method can estimate peoples age based on the face images well.
Keywords
|