Adaptive robust sparse representation for face recognition based on weighted and fusion dictionary

Changming Song, Yang Zhou, Wenguang Ji · 2026

Read Adaptive robust sparse representation for face recognition based on weighted and fusion dictionary by Changming Song, Yang Zhou, Wenguang Ji (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0351984.txt.

Description

Changming Song, Yang Zhou, and Wenguang Ji improve face recognition when examples are scarce. Their 2026 paper proposes a sparse representation model built for exactly that shortage. A fusion dictionary blends complementary views of the face data. A nuclear norm term protects fine image detail during reconstruction. Errors are modelled with a blended distribution that tolerates both small noise and gross outliers, such as occlusion or bad lighting.

The mathematics stayed friendly. The model is convex, so a classic splitting algorithm solves it reliably. The authors prove the solver converges. Head-to-head experiments then did the persuading. Their method beat rival approaches on recognition rate and on robustness together. Security and device unlocking both meet faces under poor conditions with few stored samples. A recogniser designed for scarcity, rather than despite it, fits how the technology is actually used.

Catalog record

CREATORChangming Song, Yang Zhou, Wenguang Ji
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE63019
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0351984

Browse the full library · About the Tower of Babel