In this paper, we propose an automatic age-group classification algorithm based on gender information. The proposed method detects a face region, and then it identifies eyes and lips. Using the detected eyes and lips, four regions of interest are selected from a face to extract texture features. Unlike previous efforts which try to estimate the age-group of the facial image directly, our method uses two step classification. First, the gender of the facial image is estimated. Based on the result of the gender classification, the age-group of the facial image is estimated. The experimental results show that the accuracy of age-group classification can increase about 16% in the accuracy when gender information is considered. Overall, our proposed method can achieve about 89% accuracy in age-group classification.
CITATION STYLE
Hwang, S., & Celebi, E. (2013). Automatic method of gender dependent age-group classification. In Proceedings of the 2013 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2013 (Vol. 2, pp. 668–674). CSREA Press.
Mendeley helps you to discover research relevant for your work.