Identity Document to Selfie Face Matching Across Adolescence

TL;DR

This paper addresses the challenge of matching ID document faces from early adolescence to live selfies from later adolescence, proposing a fine-tuned deep learning approach that significantly improves accuracy over existing models.

Contribution

The authors introduce a fine-tuning method using triplet loss on open-source face matchers to enhance cross-age face matching accuracy, especially for adolescent images.

Findings

Achieved 96.67% true acceptance rate at 0.01% false acceptance rate.

Outperformed the DocFace+ model on the CHIYA dataset.

Demonstrated effectiveness of few-shot fine-tuning for cross-age face matching.

Abstract

Matching live images (``selfies'') to images from ID documents is a problem that can arise in various applications. A challenging instance of the problem arises when the face image on the ID document is from early adolescence and the live image is from later adolescence. We explore this problem using a private dataset called Chilean Young Adult (CHIYA) dataset, where we match live face images taken at age 18-19 to face images on ID documents created at ages 9 to 18. State-of-the-art deep learning face matchers (e.g., ArcFace) have relatively poor accuracy for document-to-selfie face matching. To achieve higher accuracy, we fine-tune the best available open-source model with triplet loss for a few-shot learning. Experiments show that our approach achieves higher accuracy than the DocFace+ model recently developed for this problem. Our fine-tuned model was able to improve the true acceptance rate for the most difficult (largest age span) subset from 62.92% to 96.67% at a false acceptance rate of 0.01%. Our fine-tuned model is available for use by other researchers.