Effectiveness of Blind Face Restoration to Boost Face Recognition Performance at Low-Resolution Images - Inria - Institut national de recherche en sciences et technologies du numérique
Conference Papers Year : 2023

Effectiveness of Blind Face Restoration to Boost Face Recognition Performance at Low-Resolution Images

Abstract

This paper studies the effectiveness of Blind Face Restoration methods to boost the performance of face recognition systems on low-resolution images. We investigate the use of three blind face restoration techniques, which have demonstrated impressive results in generating realistic high-resolution face images. Three state-of-the-art face recognition methods were selected to assess the impact of using the generated high-resolution images on their performance. Our analysis includes both, synthesized and native low-resolution images. The conducted experimental evaluation show that this is still an open research problem.
Fichier principal
Vignette du fichier
samplepaperSR (2).pdf (3.13 Mo) Télécharger le fichier
samplepaperSR (1).pdf (3.02 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Origin Files produced by the author(s)

Dates and versions

hal-04393649 , version 1 (23-01-2024)

Licence

Identifiers

Cite

Yoanna Martínez-Díaz, Luis S. Luevano, Heydi Méndez-Vázquez. Effectiveness of Blind Face Restoration to Boost Face Recognition Performance at Low-Resolution Images. IWAIPR 2023 - International Workshop on Artificial Intelligence and Pattern Recognition, Oct 2023, Varadero, Cuba. pp.455--467, ⟨10.1007/978-3-031-49552-6_39⟩. ⟨hal-04393649⟩
59 View
109 Download

Altmetric

Share

More