AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Infant Footprint Recognition

Eryun Liu

ICCV 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 20 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add a second and third enrolled template with max-score fusion (scenario B vs A)Proposed matcher · Infant footprint matchingGAR at FAR=0.01: 60% -> 50% reported overall; S12 48% -> 53%, S23 64% -> 74%Improved
fuse six match scores (both feet, scenario C vs A)Proposed matcher · Infant footprint matchingGAR at FAR=0.01: 48% -> 61% (S12), 64% -> 83% (S23)Improved
older infants and shorter time gap (S23 vs S12 vs S13)Proposed matcher · Infant footprint matching (scenario A)GAR at FAR=0.01: 33% -> 48% -> 64%Improved
longer time gap between sessions (S13 about 4.81 months vs S12 about 1.95 months)Proposed matcher · Infant footprint matching (scenario A)GAR at FAR=0.01: 48% -> 33%Hurt
replace handcrafted local minutiae structure descriptor with learned DNN minutia descriptor (ablation)Palmprint-based footprint matcher · Infant footprint matchingROC (GAR vs FAR)Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy