A learned feature descriptor for efficient gender recognition using an RGB-D sensor
Safaa Azzakhnini, Lahoucine Ballihi, Driss Aboutajdine · 2016
In this work, the problem of feature extraction and image recognition in the context of RGB images and depth information (RGB-D images) is addressed. The purpose of this paper is to study and compare some popular techniques for gender recognition in order to understand how much depth data improves the quality of recognition, and identify which combination between face descriptors and learning techniques is best suited to better exploit RGB-D images. The experimental results show that depth data improves the recognition accuracy for gender classification applications in many use cases.