Reproduce “New Algorithmic Approaches to Point Constellation Recognition” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Thomas Bourgeat, Julien Bringer, Herve Chabanne, Robin Champenois, Jeremie Clement, Houda Ferradi, Marc Heinrich, Paul Melotti and 2 more
The authors propose three methods for matching fingerprint minutiae despite shifts, rotations, missing points, and distortion. The methods add second-order neighborhoods to recover spatial layout, use repeated mismatches to infer a shared missing minutia, and simulate one pattern as a rigid structure pulled toward another by springs. They qualitatively report an accuracy improvement for tuned second-order neighborhoods, without numerical evaluation.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.