LatentPrintFormer: A Hybrid CNN-Transformer with Spatial Attention for Latent Fingerprint identification

TL;DR

LatentPrintFormer is a hybrid CNN-Transformer model with spatial attention that effectively extracts local and global features from latent fingerprints, significantly improving identification accuracy in challenging conditions.

Contribution

The paper introduces a novel hybrid CNN-Transformer architecture with spatial attention for latent fingerprint identification, enhancing feature extraction and recognition performance.

Findings

Outperforms existing state-of-the-art methods

Achieves higher Rank-10 identification rates

Demonstrates robustness on public datasets

Abstract

Latent fingerprint identification remains a challenging task due to low image quality, background noise, and partial impressions. In this work, we propose a novel identification approach called LatentPrintFormer. The proposed model integrates a CNN backbone (EfficientNet-B0) and a Transformer backbone (Swin Tiny) to extract both local and global features from latent fingerprints. A spatial attention module is employed to emphasize high-quality ridge regions while suppressing background noise. The extracted features are fused and projected into a unified 512-dimensional embedding, and matching is performed using cosine similarity in a closed-set identification setting. Extensive experiments on two publicly available datasets demonstrate that LatentPrintFormer consistently outperforms three state-of-the-art latent fingerprint recognition techniques, achieving higher identification rates across Rank-10.