Cyclic Generative Neural Networks for Improved Face Recognition in Nonstandard Domains

A system of methods for improving the quality of face recognition from infrared images is described. For testing the recognition algorithm in a multidomain environment, a database of ordinary and infrared face images is collected. An algorithm based on cyclic generative neural networks is developed....

Full description

Saved in:
Bibliographic Details
Published in:Journal of computer & systems sciences international Vol. 57; no. 4; pp. 620 - 625
Main Authors: Grinchuk, O. V., Tsurkov, V. I.
Format: Journal Article
Language:English
Published: Moscow Pleiades Publishing 01.07.2018
Springer Nature B.V
Subjects:
Algorithms
Control
Engineering
Face recognition
Facial recognition technology
Image quality
Infrared imagery
Mechatronics
Neural networks
Object recognition
Pattern Recognition and Image Processing
Robotics
ISSN:1064-2307, 1555-6530
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A system of methods for improving the quality of face recognition from infrared images is described. For testing the recognition algorithm in a multidomain environment, a database of ordinary and infrared face images is collected. An algorithm based on cyclic generative neural networks is developed. This algorithm makes it possible to transform images from the color domain into the infrared domain, which significantly increases the size of the training sample. It is shown that fine-tuning the recognition algorithm using the generated infrared images improves the recognition result on the test sample.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1064-2307
1555-6530
DOI:10.1134/S1064230718040093