afis

AFIS toolkit for fingerprint minutiae extraction, matching, and quality assessment. Classical extractors (NBIS/MINDTCT, Gabor, STFT, SAFIS) plus optional LEADER ONNX.

Install

pip install afis
# or
uv add afis

# Optional: LEADER deep minutiae extractor
pip install 'afis[leader]'

From source (includes the optional native NBIS library):

make install          # uv sync + make native

Quickstart

from afis import NbisExtractor, MindtctExtractor, SafisExtractor, compute_nfiq2

# NIST NBIS (native) — requires make native
nbis = NbisExtractor()
a = nbis.extract_minutiae("finger_a.png")
b = nbis.extract_minutiae("finger_b.png")
print(a.n_minutiae, a.header.image_quality)
print(nbis.match(a, b))

# Pure-Python NBIS-compatible (no native lib)
py = MindtctExtractor()
t = py.extract_minutiae("finger_a.png")

# SourceAFIS-equivalent edge matching (not Bozorth3)
safis = SafisExtractor()
s = safis.extract_minutiae("finger_a.png")
print(safis.match(s, s))

# LEADER ONNX (requires: pip install 'afis[leader]')
from afis import LeaderExtractor
leader = LeaderExtractor()
lt = leader.extract_minutiae("finger_a.png")
print(lt.n_minutiae, leader.match(lt, lt))

# Quality only (NFIQ2, 0–100)
q = compute_nfiq2(image)
print(q.score)

Choose a stack

Mix and match freely:

from afis import NbisExtractor

# Classical Gabor enhance + MCC matching
proc = NbisExtractor(extractor="gabor", matcher="mcc")

# STFT enhance + geometric matcher
proc = NbisExtractor(extractor="stft", matcher="geometric")

# LEADER extract + Bozorth3 match
proc = NbisExtractor(extractor="leader", matcher="bozorth3")

Extractors

Matchers

Quality (NFIQ2)

compute_nfiq2(image) and every extractor report return a unified 0–100 score (ISO/IEC 29794-4 / NFIQ 2 style), with actionable feedback when available.

from afis import compute_nfiq2

r = compute_nfiq2(image)
print(r.score, r.actionable)

Use cases

CLI

afis extract finger.png finger.xyt
afis extract finger.png out.xyt --extractor mindtct
afis extract finger.png out.xyt --extractor leader
afis match a.xyt b.xyt --method bozorth3 --height 480
afis match a.xyt b.xyt --method safis
afis match a.xyt b.xyt --method mcc
afis quality finger.png

Develop

make install
make test
make build

References

• NIST NBIS — MINDTCT / LFS V2 / Bozorth3. NIST Biometric Image Software
• NFIQ 2 / ISO/IEC 29794-4 — Finger image quality. usnistgov/NFIQ2
• SourceAFIS — Edge-pairing matcher algorithm (Važan). algorithm
• MCC — Cappelli, Ferrara & Maltoni (2010). Minutia Cylinder-Code. IEEE TPAMI. https://doi.org/10.1109/TPAMI.2010.52
• LEADER — Fully convolutional minutiae detector (pyfing). pyfing
• Gabor enhancement — Hong, Wan & Jain (1998). Fingerprint image enhancement. IEEE TPAMI
• ISO/IEC 19794-2 — Finger minutiae data interchange
• FVC / FVC-onGoing — Verification benchmarks (EER, FMR, FNMR)

License

MIT. Copyright (c) 2026 Ashok Pant.