Analysis of the effect of image resolution on automatic face gender and age classification

In this paper, the effect of the image resolution for gender detection and age classification have been analyzed by conducting experiments with facial images that have 10 different image resolutions ranging from 2 × 1 to 329 × 264. K Nearest Neighbor (k-NN), Support Vector Machine (SVM) and Random Forests (RF) classifiers, which have been successfully used in several applications, have been employed to extract gender and age information from the images. Experiments for age classification and gender detection have been performed separately.