Deep Learning for Understanding Faces: Machines May Be Just as Good, or Better, than Humans

TY - JOUR

T1 - Deep Learning for Understanding Faces

T2 - Machines May Be Just as Good, or Better, than Humans

AU - Ranjan, Rajeev

AU - Sankaranarayanan, Swami

AU - Bansal, Ankan

AU - Bodla, Navaneeth

AU - Chen, Jun Cheng

AU - Castillo, Carlos D.

AU - Chellappa, Rama

N1 - Funding Information: Vishal M. Patel (vishal.m.patel@rutgers.edu) received his B.S. degrees in electrical engineering and applied mathematics (with honors) and his M.S. degree in applied mathematics from North Carolina State University, Raleigh, in 2004 and 2005, respectively. He is an A. Walter Tyson Assistant Professor in the Department of Electrical and Computer Engineering at Rutgers University, Piscataway, New Jersey. Prior to joining Rutgers, he was a member of the research faculty at the University of Maryland Institute for Advanced Computer Studies. His research interests are in signal processing, computer vision, and machine learning with applications to radar imaging and biometrics. He received the 2016 Office of Naval Research Young Investigator Award and the 2010 Oak Ridge Associated Universities postdoctoral fellowship. Funding Information: We acknowledge the help of Anirudh Nanduri, Amit Kumar, Wei-An Lin, Pouya Samangouei, Emily M. Hand, and Ching-Hui Chen. This research is based upon work supported by the Office of the Director of National Intelligence (ODNI), Intelligence Advanced Research Projects Activity (IARPA), via IARPA R&D contract number 2014-14071600012. The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of the ODNI, IARPA, or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for governmental purposes notwithstanding any copyright annotation thereon. Publisher Copyright: © 1991-2012 IEEE.

PY - 2018/1

Y1 - 2018/1

N2 - Recent developments in deep convolutional neural networks (DCNNs) have shown impressive performance improvements on various object detection/recognition problems. This has been made possible due to the availability of large annotated data and a better understanding of the nonlinear mapping between images and class labels, as well as the affordability of powerful graphics processing units (GPUs). These developments in deep learning have also improved the capabilities of machines in understanding faces and automatically executing the tasks of face detection, pose estimation, landmark localization, and face recognition from unconstrained images and videos. In this article, we provide an overview of deep-learning methods used for face recognition. We discuss different modules involved in designing an automatic face recognition system and the role of deep learning for each of them. Some open issues regarding DCNNs for face recognition problems are then discussed. This article should prove valuable to scientists, engineers, and end users working in the fields of face recognition, security, visual surveillance, and biometrics.

AB - Recent developments in deep convolutional neural networks (DCNNs) have shown impressive performance improvements on various object detection/recognition problems. This has been made possible due to the availability of large annotated data and a better understanding of the nonlinear mapping between images and class labels, as well as the affordability of powerful graphics processing units (GPUs). These developments in deep learning have also improved the capabilities of machines in understanding faces and automatically executing the tasks of face detection, pose estimation, landmark localization, and face recognition from unconstrained images and videos. In this article, we provide an overview of deep-learning methods used for face recognition. We discuss different modules involved in designing an automatic face recognition system and the role of deep learning for each of them. Some open issues regarding DCNNs for face recognition problems are then discussed. This article should prove valuable to scientists, engineers, and end users working in the fields of face recognition, security, visual surveillance, and biometrics.

UR - http://www.scopus.com/inward/record.url?scp=85040703866&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040703866&partnerID=8YFLogxK

U2 - https://doi.org/10.1109/MSP.2017.2764116

DO - https://doi.org/10.1109/MSP.2017.2764116

M3 - Article

SN - 1053-5888

VL - 35

SP - 66

EP - 83

JO - IEEE Signal Processing Magazine

JF - IEEE Signal Processing Magazine

IS - 1

M1 - 8253595

ER -