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

Rajeev Ranjan, Swami Sankaranarayanan, Ankan Bansal, Navaneeth Bodla, Jun Cheng Chen, Carlos D. Castillo, Rama Chellappa

Research output: Contribution to journalArticlepeer-review

68 Scopus citations


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.

Original languageAmerican English
Article number8253595
Pages (from-to)66-83
Number of pages18
JournalIEEE Signal Processing Magazine
Issue number1
StatePublished - Jan 2018

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering
  • Applied Mathematics


Dive into the research topics of 'Deep Learning for Understanding Faces: Machines May Be Just as Good, or Better, than Humans'. Together they form a unique fingerprint.

Cite this