# LEADER: Lightweight End-to-End Attention-Gated Dual Autoencoder for Robust Minutiae Extraction

arXiv: https://arxiv.org/abs/2602.15493 · HTML: https://mlsanity.com/paper/2602.15493/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 41 references that are in the map.
- First posted on arXiv 17 Feb 2026.

## Builds on (most cited first, 9 of 9)

- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Symbolic Discovery of Optimization Algorithms](https://mlsanity.com/paper/2302.06675/) (2023)
- [FingerNet: An Unified Deep Network for Fingerprint Minutiae Extraction](https://mlsanity.com/paper/1709.02228/) (2017)
- [End-to-End Latent Fingerprint Search](https://mlsanity.com/paper/1812.10213/) (2018)
- [Robust Minutiae Extractor: Integrating Deep Networks and Fingerprint Domain Knowledge](https://mlsanity.com/paper/1712.09401/) (2017)
- [Latent fingerprint minutia extraction using fully convolutional network](https://mlsanity.com/paper/1609.09850/) (2016)
- [Filter Design and Performance Evaluation for Fingerprint Image Segmentation](https://mlsanity.com/paper/1501.02113/) (2015)
- [Standard Fingerprint Databases: Manual Minutiae Labeling and Matcher Performance Analyses](https://mlsanity.com/paper/1305.1443/) (2013)

## Built on by (most cited first, 1 of 1)

- [Revisiting Handcrafted Minutiae Detection: A Simple and Effective Open Source Baseline for Modern Fingerprint Workflows](https://mlsanity.com/paper/2610.11641/) (2026)

## Abstract (arXiv)

Minutiae extraction, a fundamental stage in fingerprint recognition, is increasingly shifting toward deep learning. However, truly end-to-end methods that eliminate separate preprocessing and postprocessing steps remain scarce. This paper introduces LEADER (Lightweight End-to-end Attention-gated Dual autoencodER), a neural network that maps raw fingerprint images to minutiae descriptors, including location, direction, and type. The proposed architecture integrates non-maximum suppression and angular decoding to enable complete end-to-end inference using only 0.9M parameters. It employs a novel "Castle-Moat-Rampart" ground-truth encoding and a dual-autoencoder structure, interconnected through an attention-gating mechanism. Experimental evaluations demonstrate state-of-the-art accuracy on plain fingerprints and robust cross-domain generalization to latent impressions. Specifically, LEADER attains a 34% higher F1-score on the NIST SD27 dataset compared to specialized latent minutiae extractors. Sample-level analysis on this challenging benchmark reveals an average rank of 2.07 among all compared methods, with LEADER securing the first-place position in 47% of the samples-more than doubling the frequency of the second-best extractor. The internal representations learned by the model align with established fingerprint domain features, such as segmentation masks, orientation fields, frequency maps, and skeletons. Inference requires 15ms on GPU and 322ms on CPU, outperforming leading commercial software in computational efficiency. The source code and pre-trained weights are publicly released to facilitate reproducibility.