In this paper; we propose a method that estimates gender and age based on facial images. Our method uses the four directional features (FDF) and linear discriminant analysis (LDA). FDF is extracted from the detected face region and the area included the eyes and mouth. We evaluated the performance of the age and gender estimation method by the combination of the facial images classes divided by age and gender. Experiments showed that the gender estimation rate was achieved at 92 and age estimation rate was approximately 70 for training persons and approximately 40 for unknown persons.
展开▼