Facial mark based biometric differentiation of identical twins using dynamic feature enhancement

TL;DR

This paper presents a machine learning framework that can distinguish identical twins using facial skin marks with high accuracy.

Contribution

A novel machine learning framework using facial skin marks and dynamic feature enhancement to differentiate identical twins.

Findings

The framework achieved 96.62% cross-validation accuracy and 90.6% AUC score.

Random search optimization provided the best performance-efficiency trade-off with 90.6% AUC and 88.4% test accuracy.

Abstract

This comprehensive study demonstrates an advanced machine learning framework for distinguishing identical twins using facial skin marks, achieving 96.62% cross-validation accuracy and 90.6% AUC score. The methodology incorporates four distinct hyperparameter optimization techniques (random search, Bayesian optimization, particle swarm optimization, and grid search), comprehensive statistical validation, and a robust preprocessing pipeline including PCA and SMOTE. Analysis of 74 twin pairs from 319 processed images using automated facial mark detection and multi-metric similarity assessment reveals spatial distribution patterns as the primary discriminating factor. The framework employs sophisticated feature engineering (32\documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\rightarrow$$\end{document}15\documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\rightarrow$$\end{document}6 dimensions) and achieves statistically significant performance (p < 0.001) with minimal overfitting. Random search optimization emerged as the optimal method, providing the best performance-efficiency trade-off with 90.6% AUC, 88.4% test accuracy, and the fastest execution time (31.8s). The system demonstrates production-ready computational efficiency and establishes a reliable foundation for forensic biometric applications with comprehensive statistical validation and deployment specifications. Figure 1 depicts the graphical abstract.

Figures