摘要
由于人脸面貌特征与年龄存在着较大的不确定性,提出了基于模糊隶属度的人脸图像年龄估计.用对光照、尺度变化具有很强鲁棒性的Gabor小波变换提取人脸特征,为了避免维数灾难,降低后续计算量,利用主成份分析方法对提取到的特征进行降维,细致推导了适用于人脸图像年龄估计的模糊函数,根据最大隶属度原则,来估计人脸的年龄.在FG-NET人脸库及自建的FAID人脸库中进行了实验,取得了94%的最高识别率.
Because of the greater uncertainty exists in both face features and age, a novel method based on fuzzy membership degrees for age estimation of face image is proposed. Face features are extracted by Gabor wavelet transform which are robust to the illumination change and scale variations. In order to avoid dimensions disaster and reduce the follow-up calculation, the dimensions of the extracted features are reduced by means of principal component analysis. The fuzzy function is appropriate for age estimation of face image was derived rigorous. The principle of maximum membership degree is used to age estimation, the experiments were conducted on the FG-NET face database and own FAID face database, the highest recognition rate of 94% was achieved.
出处
《计算机系统应用》
2013年第5期207-210,共4页
Computer Systems & Applications
基金
山西大同大学科研项目(2012K8)
关键词
GABOR小波变换
特征提取
模糊隶属度
年龄估计
gabor wavelet transform
features extraction
fuzzy membership degrees
age estimation
