A Bayesian algorithm for detecting identity matches and fraud in image databases
arXiv:1706.06230v11 citations
Originality Synthesis-oriented
AI Analysis
This addresses fraud detection in image databases, but appears incremental as it builds on existing matching algorithms without claiming major breakthroughs.
The paper tackles the problem of detecting identity matches and fraud in image databases by presenting a statistical algorithm based on a generative graph model, but no concrete results or numbers are provided in the abstract.
A statistical algorithm for categorizing different types of matches and fraud in image databases is presented. The approach is based on a generative model of a graph representing images and connections between pairs of identities, trained using properties of a matching algorithm between images.