We present a novel learning system for human demographic estimation in which the ethnicity, gender and age attributes are estimated from facial images. The proposed approach consists of the following three main stages: 1) face alignment and preprocessing; 2) constructing a Pyramid Multi-Level face representation from which the local features are extracted from the blocks of the whole pyramid; 3) feeding the obtained features to an hierarchical estimator having three layers. Due to the fact that ethnicity is by far the easiest attribute to estimate, the adopted hierarchy is as follows. The first layer predicts ethnicity of the input face. Based on that prediction, the second layer estimates the gender using the corresponding gender classifier. Based on the predicted ethnicity and gender, the age is finally estimated using the corresponding regressor. Experiments are conducted on five public databases (MORPH II, PAL, IoG, LFW and FERET) and another two challenge databases (Apparent age; Smile and Gender) of the 2016 ChaLearn Looking at People and Faces of the World Challenge and Workshop. These experiments show stable and good results. We present many comparisons against state-of-the-art methods. We also provide a study about cross-database evaluation. We quantitatively measure the performance drop in age estimation and in gender classification when the ethnicity attribute is misclassified.