3D face reconstruction and recognition using the overfeat network

Abstract

Although face recognition is considered a popular area of research and study, it still has few unresolved challenges, and with the appearance of devices such as the Microsoft Kinect, new possibilities for researchers were uncovered. With the goal of enhancing face recognition techniques, this paper presents a novel way to reconstruct face images in different angles, through the use of the data of one front image captured by the Kinect, using faster techniques than ever before, also, this paper utilizes a deep learning network called Overfeat, where it functioned as a feature extractor that was used on normal images and on the new 3D created images, which introduced a new application for the network. To check the capabilities of the new created images, they were used as a testing set in three main experiments. Finally, results of the experiments are presented to prove the ability of the created images to function as new data sets for face recognition; also, proving the capability of the Overfeat network, working with computer generated face images.