Robust single-sample face recognition by sparsity-driven sub-dictionary learning using deep features

Jianyi Lin, Alessandro D'Amelio, V. Cuculo, G. Grossi, R. Lanzarotti

Risultato della ricerca: Contributo in rivistaArticolo in rivista

9 Citazioni (Scopus)

Abstract

Face recognition using a single reference image per subject is challenging, above all when referring to a large gallery of subjects. Furthermore, the problem hardness seriously increases when the images are acquired in unconstrained conditions. In this paper we address the challenging Single Sample Per Person (SSPP) problem considering large datasets of images acquired in the wild, thus possibly featuring illumination, pose, face expression, partial occlusions, and low-resolution hurdles. The proposed technique alternates a sparse dictionary learning technique based on the method of optimal direction and the iterative ℓ 0 -norm minimization algorithm called k-LIMAPS. It works on robust deep-learned features, provided that the image variability is extended by standard augmentation techniques. Experiments show the effectiveness of our method against the hardness introduced above: first, we report extensive experiments on the unconstrained LFW dataset when referring to large galleries up to 1680 subjects; second, we present experiments on very low-resolution test images up to 8 × 8 pixels; third, tests on the AR dataset are analyzed against specific disguises such as partial occlusions, facial expressions, and illumination problems. In all the three scenarios our method outperforms the state-of-the-art approaches adopting similar configurations.
Lingua originaleEnglish
pagine (da-a)1-19
Numero di pagine19
RivistaSensors
Volume19
DOI
Stato di pubblicazionePubblicato - 2019

Keywords

  • Deep convolutional neural network (DCNN) features
  • Dictionary learning
  • Face recognition
  • Optimal directions (MOD)
  • Single sample per person
  • Sparse recovery
  • Pattern Recognition, Automated
  • Biometric Identification
  • Databases, Factual
  • Humans
  • Deep Learning
  • Facial Recognition
  • Image Processing, Computer-Assisted
  • Algorithms

Fingerprint Entra nei temi di ricerca di 'Robust single-sample face recognition by sparsity-driven sub-dictionary learning using deep features'. Insieme formano una fingerprint unica.

Cita questo