Parallel deep learning architecture with customized and learnable filters for low-resolution face recognition

Face recognition in visual surveillance systems is important for various applications to identify individuals who are behaving defiantly at the time of an event or for investigation purposes. Despite the dramatic improvements in facial recognition technology in recent years, it is difficult to recog...

Full description

Saved in:
Bibliographic Details
Published inThe Visual computer Vol. 39; no. 12; pp. 6699 - 6710
Main Authors Ketab, Faris, Russel, Newlin Shebiah, Selvaraj, Arivazhagan, Buhari, Seyed Mohamed
Format Journal Article
LanguageEnglish
Published Berlin/Heidelberg Springer Berlin Heidelberg 01.12.2023
Springer Nature B.V
Subjects
Artificial Intelligence
Cameras
Computer Graphics
Computer networks
Computer Science
Customization
Deep learning
Face recognition
Facial recognition technology
Gabor filters
Gabor transformation
Image Processing and Computer Vision
Neural networks
Original Article
Surveillance
Surveillance systems
Low-resolution face recognition
Surveillance
Gabor filters
Convolutional neural network
Online AccessGet full text

Cover

More Information
Summary:Face recognition in visual surveillance systems is important for various applications to identify individuals who are behaving defiantly at the time of an event or for investigation purposes. Despite the dramatic improvements in facial recognition technology in recent years, it is difficult to recognize faces from surveillance feeds due to the presence of multiple people of different scales and orientations. This paper solves the task of low-resolution face recognition by combining exemplary techniques for extracting distinct features. This research utilizes the attributes learned by customized and learnable filters and injected in the training process to better match them with human brain functionality. The Gabor transform aims to convolve a facial image using a range of Gabor filter coefficients at various scales and orientations, resulting in scale and rotation invariant features. The tailored architecture with residual stream aims to enhance functional representation and prevent the gradient of the prediction engine from affecting the backbone network functional map. Experimental analysis is performed on the SCface and TinyFace databases and is reported with an accuracy of 89.21% on the SCface database and 56.68% on the TinyFace database.
ISSN:0178-2789
1432-2315
DOI:10.1007/s00371-022-02757-y