Saved in:
Bibliographic Details
Main Authors: Maity, Arnab, Manasa, C, Pavan Kumar, Ramachandra, Raghavendra
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.08119
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914150809075712
author Maity, Arnab
Manasa
C, Pavan Kumar
Ramachandra, Raghavendra
author_facet Maity, Arnab
Manasa
C, Pavan Kumar
Ramachandra, Raghavendra
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_08119
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LatentPrintFormer: A Hybrid CNN-Transformer with Spatial Attention for Latent Fingerprint identification
Maity, Arnab
Manasa
C, Pavan Kumar
Ramachandra, Raghavendra
Computer Vision and Pattern Recognition
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.
title LatentPrintFormer: A Hybrid CNN-Transformer with Spatial Attention for Latent Fingerprint identification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.08119