Descripors and regions of interest fusion for gender classification in the wild.

Gender classification (GC) has achieved high accuracy in different experimental evaluations based mostly on inner facial details. However, these results are not generalized in unrestricted datasets and particularly in cross-database experiments, where the performance drops drastically. In this paper, we analyze the state-of-the-art GC accuracy on three large datasets: MORPH, LFW and GROUPS. We discuss their respective difficulties and bias, concluding that the most challenging and wildest complexity is present in GROUPS. This dataset covers hard conditions such as low resolution imagery and cluttered background. We further analyze in depth the performance of different descriptors extracted from the face and its local context on this dataset. Selecting the bests and studying their most suitable combination allows us to design a solution that beats any previously published results, reaching an accuracy over 94.2%, reducing the gap with other simpler datasets. This improvement is later confirmed with the final and extensive cross-database experimental evaluation.