In traditional age estimation methods which utilize discriminative methods
for feature extraction, the biological age labels are adopted as the ground truth for
supervision. However, the appearance age, which is indicated by the facial appearance,
is intrinsically a fuzzy attribute of human faces which is inadequate to be labeled as a
crisp value. To address this issue, this paper firstly introduces a fuzzy representation of
age labels and then extends the LDA into fuzzy ones. In the definition of fuzzy labels,
both the ongoing property of facial aging and the ambiguity between facial appearance
and biological age are considered. By utilizing the fuzzy labels for supervision, the
proposed method outperforms the crisp ones in both preserving ordinal information of
aging faces and adjusting the inconsistency between the biological age and appearance.
Experiments on both FG-NET and MORPH databases confirm the effectiveness of the
proposed method.
Keywords: Age information, Aging pattern subspace, Appearance age, Biological
age, Conformal embedding analysis, Cumulative score, Facial age estimation,
Facial appearance, Facial landmark, Facial shape, Fuzziness in Facial aging,
Fuzzy discriminant analysis, Fuzzy LDA, Fuzzy representation of age labels,
Intra-class and inter-Class neighbors, Linear discriminant analysis, Marginal
Fisher analysis, Mean absolute error, Ordinary preserving LDA, Ordinary
preserving MFA.
