LatentPrintFormer: A Hybrid CNN-Transformer with Spatial Attention for Latent Fingerprint identification
This addresses the problem of low-quality latent fingerprint identification for forensic applications, representing an incremental improvement.
The paper tackled latent fingerprint identification by proposing LatentPrintFormer, a hybrid CNN-Transformer model with spatial attention, which achieved higher identification rates than three state-of-the-art methods on two public datasets.
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.