EUVIMEDDescoperă EUVIMED
Open access · CC BY 4.0

Compact Fingerprint Identification With a Parameter‐Free LBP Front End: A Source‐Level Controlled Ablation Study of Representations and Classifier Heads

Abouzar Zareei, Mohammad Hossein Shakoor

IET Biometrics · 2026-01 · 2026 (1)

DOI: 10.1049/bme2/6557121 ↗

At a glance

Journal article in IET Biometrics, published online on 2026-11-15. Written by Abouzar Zareei and 1 co-authors. 63 references. The full text is freely available (open access, CC BY 4.0).

RezumatDate bibliograficeCiteRelated studies

Abstract (original language)

This study investigates a parameter‐free local binary pattern (LBP) front end for compact closed‐set fingerprint identification under a source‐impression‐level leakage‐controlled protocol. The official FVC2000 DB4_B set provides 80 original impressions from 10 fingers. For each of five seeded partitions, five impressions per finger are used for training, one for validation and two for testing. Ten deterministic views are generated only after source partitioning, yielding frozen 500/100/200‐image arrays; the 20 held‐out source impressions, rather than their 200 correlated views, define the primary evaluation unit. Twenty CNN configurations form 10 matched GAP/flatten pairs spanning raw inputs, scalar and bit‐plane LBP, multiscale encoding and backbone depth. All receive 200 epochs of online translation augmentation plus five unaugmented epochs; the checkpoint with minimum validation loss is used for primary evaluation. The deeper normalized‐raw Flatten model achieves 91.0% ± 6.5% source‐level accuracy, whereas a standard unnormalized‐raw GAP model achieves 84.0% ± 4.2% with 19,466 parameters. GAP substantially reduces classifier capacity but does not consistently improve accuracy; effects depend on input encoding and network depth. Statistical comparisons across five repeated splits are interpreted descriptively owing to their limited resolution.

Cite

APA

Zareei, A., & Shakoor, M. H. (2026). Compact Fingerprint Identification With a Parameter‐Free LBP Front End: A Source‐Level Controlled Ablation Study of Representations and Classifier Heads. IET Biometrics, 2026(1). https://doi.org/10.1049/bme2/6557121

Vancouver

Zareei A, Shakoor MH. Compact Fingerprint Identification With a Parameter‐Free LBP Front End: A Source‐Level Controlled Ablation Study of Representations and Classifier Heads. IET Biometrics. 2026;2026(1). doi:10.1049/bme2/6557121

BibTeX
@article{Zareei2026,
  author = {Zareei, Abouzar and Shakoor, Mohammad Hossein},
  title = {Compact Fingerprint Identification With a Parameter‐Free LBP Front End: A Source‐Level Controlled Ablation Study of Representations and Classifier Heads},
  journal = {IET Biometrics},
  year = {2026},
  volume = {2026},
  number = {1},
  doi = {10.1049/bme2/6557121}
}
Start for free →