The last decade witnessed a renaissance of machine learning for image processing. Super-resolution (SR) is one of the areas where deep learning techniques have achieved impressive results, with a speci fi c focus on the SR of facial images. Examining and comparing facial images is one of the critical activities in forensic video analysis; a compelling question is thus whether recent SR techniques could help face recognition (FR) made by a human operator, especially in the challenging scenario where very low resolution images are available, which is typical of surveillance recordings. This paper addresses such a question through a simple yet insightful experiment: we used two state- of-the-art deep learning-based SR algorithms to enhance some very low-resolution faces of 30 worldwide celebrities. We then asked a heterogeneous group of more than 130 individuals to recognize them and compared the recognition accuracy against the one achieved by presenting a simple bicubic-interpolated version of the same faces. Results are somehow surprising: despite an undisputed general superiority of SR-enhanced images in terms of visual appearance, SR techniques brought no considerable advantage in overall recognition accuracy.

Does Deep Learning-Based Super-Resolution Help Humans With Face Recognition?

Sergio Carrato;
2022

Abstract

The last decade witnessed a renaissance of machine learning for image processing. Super-resolution (SR) is one of the areas where deep learning techniques have achieved impressive results, with a speci fi c focus on the SR of facial images. Examining and comparing facial images is one of the critical activities in forensic video analysis; a compelling question is thus whether recent SR techniques could help face recognition (FR) made by a human operator, especially in the challenging scenario where very low resolution images are available, which is typical of surveillance recordings. This paper addresses such a question through a simple yet insightful experiment: we used two state- of-the-art deep learning-based SR algorithms to enhance some very low-resolution faces of 30 worldwide celebrities. We then asked a heterogeneous group of more than 130 individuals to recognize them and compared the recognition accuracy against the one achieved by presenting a simple bicubic-interpolated version of the same faces. Results are somehow surprising: despite an undisputed general superiority of SR-enhanced images in terms of visual appearance, SR techniques brought no considerable advantage in overall recognition accuracy.
Pubblicato
https://www.frontiersin.org/articles/10.3389/frsip.2022.854737/full
File in questo prodotto:
File Dimensione Formato  
2022_fsp.pdf

accesso aperto

Descrizione: articolo
Tipologia: Documento in Versione Editoriale
Licenza: Creative commons
Dimensione 2.59 MB
Formato Adobe PDF
2.59 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11368/3026704
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact