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.
2 Lanitis A, Taylor CJ, Cootes T. Toward automatic simulation of aging effects on face image. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(4):442-455.
3 Fu Y, Xu Y, Huang TS. Estimating human age by manifold analysis of face pictures and regression on aging features. The IEEE International Conference on Multimedia and Expo (ICME) 2007.
6 Choi SE, Lee YJ, Lee SJ, et al. Age estimation using a hierar-chical classifier based on global and local facial features. Pattern Recognition,2011,44:1262-1281.