AI and machine learning help scientists understand human face recognition

AI and Machine Learning have helped scientists to better understand how human brain perform face recognition
Face sets used to examine the tensor decomposition algorithm. (a) Sample set. Shows 64 out of 128 faces serving as input to the algorithm to create the tensorfaces. (b) Test set: A different set of faces to evaluate properties of the tensorfaces. Credit: Skolkovo Institute of Science and Technology

Scientists from Salk Institute (U.S.), Skoltech (Russia), and the Riken Center for Brain Science (Japan) investigated a theoretical model of how populations of neurons in the visual cortex of the brain may recognize and process faces and their expressions, and how they are organized. The research was recently published in Neural Computation and highlighted on its cover.

Humans have amazing capacity to recognize a huge number of individual faces and interpret facial expressions. These abilities play a key role in human social interactions. However, how the human brain processes and stores such complex visual information is still poorly understood.

Skoltech scientists Anh-Huy Phan and Andrzej Cichocki, with their colleagues from the U.S. and Japan, Sidney Lehky and Keiji Tanaka, sought to better understand how the visual cortex processes and stores information related to face recognition. Their approach was based on the idea that a can be conceptually represented as a collection of parts or components, including eyes, eyebrow, nose, mouth, etc. Using a machine learning approach, they applied a novel tensor algorithm to decompose faces into a set of components or images called tensorfaces, as well as their associated weights, and represented faces by linear combinations of those components. In this way, they built a describing the work of the neurons involved in face recognition.

"We used novel tensor decompositions to represent faces as a set of components with specified complexity, which can be interpreted as model face cells and indicate that human face representations consist of a mixture of low- and medium-complexity face cells," said Skoltech Professor Andrzej Cichocki.

More information: Sidney R. Lehky et al. Face Representations via Tensorfaces of Various Complexities, Neural Computation (2019). DOI: 10.1162/neco_a_01258

Citation: AI and machine learning help scientists understand human face recognition (2020, March 2) retrieved 24 July 2024 from
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.

Explore further

Neuroscientists 3-D model 'face identity information' stored in the brain


Feedback to editors