融合卷积与注意力机制，提升模糊指纹的识别准确率。
LatentPrintFormer: A Hybrid CNN-Transformer with Spatial Attention for Latent Fingerprint identification
- 结合CNN与Transformer提取局部和全局特征，增强指纹细节感知。
- 在两个公开数据集上Rank-10识别率超越现有方法，最高提升6.2%。
- 适合法医指纹分析、公安系统等需要高精度识别的场景。
由于图像质量低、背景噪声干扰及印痕不完整，潜指纹识别仍具挑战性。本文提出LatentPrintFormer，融合EfficientNet-B0（CNN）与Swin Tiny（Transformer）双骨干网络，联合提取潜指纹的局部与全局特征。引入空间注意力模块，强化高质量纹线区域，抑制背景噪声。特征经融合与投影生成统一的512维嵌入向量，采用余弦相似度在闭集设定下进行匹配。在两个公开数据集上的大量实验表明，LatentPrintFormer持续优于三种先进潜指纹识别方法，在Rank-10识别率上表现更优。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。