Consiglio Nazionale delle Ricerche

Tipo di prodottoArticolo in rivista
TitoloCross-resolution learning for face recognition
Anno di pubblicazione2020
FormatoElettronico
Autore/iMassoli F.V.; Amato G.; Falchi F.
Affiliazioni autoriCNR-ISTI, Pisa, Italy; CNR-ISTI, Pisa, Italy; CNR-ISTI, Pisa, Italy
Autori CNR e affiliazioni
  • FABIO VALERIO MASSOLI
  • GIUSEPPE AMATO
  • FABRIZIO FALCHI
Lingua/e
  • inglese
AbstractConvolutional Neural Network models have reached extremely high performance on the Face Recognition task. Mostly used datasets, such as VGGFace2, focus on gender, pose, and age variations, in the attempt of balancing them to empower models to better generalize to unseen data. Nevertheless, image resolution variability is not usually discussed, which may lead to a resizing of 256 pixels. While specific datasets for very low-resolution faces have been proposed, less attention has been paid on the task of cross-resolution matching. Hence, the discrimination power of a neural network might seriously degrade in such a scenario. Surveillance systems and forensic applications are particularly susceptible to this problem since, in these cases, it is common that a low-resolution query has to be matched against higher-resolution galleries. Although it is always possible to either increase the resolution of the query image or to reduce the size of the gallery (less frequently), to the best of our knowledge, extensive experimentation of cross-resolution matching was missing in the recent deep learning-based literature. In the context of low- and cross-resolution Face Recognition, the contribution of our work is fourfold: i) we proposed a training procedure to fine-tune a state-of-the-art model to empower it to extract resolution-robust deep features; ii) we conducted an extensive test campaign by using high-resolution datasets (IJB-B and IJB-C) and surveillance-camera-quality datasets (QMUL-SurvFace, TinyFace, and SCface) showing the effectiveness of our algorithm to train a resolution-robust model; iii) even though our main focus was the cross-resolution Face Recognition, by using our training algorithm we also improved upon state-of-the-art model performances considering low-resolution matches; iv) we showed that our approach could be more effective concerning preprocessing faces with super-resolution techniques. The python code of the proposed method will be available at https://github.com/fvmassoli/cross-resolution-face-recognition.
Lingua abstractinglese
Altro abstract-
Lingua altro abstract-
Pagine da-
Pagine a-
Pagine totali15
RivistaImage and vision computing
Attiva dal 1983
Editore: Elsevier - Amsterdam
Paese di pubblicazione: Paesi Bassi
Lingua: inglese
ISSN: 0262-8856
Titolo chiave: Image and vision computing
Titolo proprio: Image and vision computing.
Titolo abbreviato: Image vis. comput.
Numero volume della rivista99
Fascicolo della rivista-
DOI10.1016/j.imavis.2020.103927
Verificato da refereeSì: Internazionale
Stato della pubblicazionePublished version
Indicizzazione (in banche dati controllate)
  • Scopus (Codice:2-s2.0-85085261425)
  • ISI Web of Science (WOS) (Codice:000541130800003)
Parole chiaveDeep learning, Low resolution face recognition, Cross resolution face recognition
Link (URL, URI)https://www.sciencedirect.com/science/article/abs/pii/S0262885620300597
Titolo parallelo-
Licenza-
Scadenza embargo-
Data di accettazione-
Note/Altre informazioniprogetto europeo AI4EU (G.A. ID 825619) da inserire
Strutture CNR
  • ISTI — Istituto di scienza e tecnologie dell'informazione "Alessandro Faedo"
Moduli/Attività/Sottoprogetti CNR-
Progetti Europei
Allegati
Cross-resolution learning for face recognition (documento privato )
Descrizione: Published version
Tipo documento: application/pdf
preprint
Descrizione: preprint version
Tipo documento: application/pdf