Compact Minutiae Descriptor for Fingerprint Matching on Resource-Constrained Microcontrollers

DOI: https://doi.org/10.62517/jes.202602310

Author(s)

Junda Li, Wen Li*, Jing Jia, Suhui Fan, Xiaoran Cui

Affiliation(s)

School of Electrical Engineering, Yingkou Institute of Technology, Yingkou, China *Corresponding Author.

Abstract

Fingerprint-based biometric authentication is increasingly demanded in IoT and embedded devices, yet state-of-the-art matching algorithms require memory and compute resources that far exceed typical microcontroller capabilities. We present a lightweight fingerprint matching framework designed for ARM Cortex-M class microcontrollers with sub-1 MB SRAM. Our approach introduces four components: (1) a Compact Minutiae Descriptor (CMD) that reduces per-minutia storage from 48 bytes to 14 bytes through angular quantization and local topology encoding; (2) a fixed-point scoring engine using lookup tables that eliminates floating-point dependencies; (3) a hierarchical two-level indexing scheme that prunes 88% of candidates before detailed matching; and (4) a memory-aware enrollment strategy that adaptively adjusts template precision to fit available SRAM. Evaluated via cycle-accurate simulation on 12 FVC benchmark databases (FVC2000, FVC2002, FVC2004) with score distributions calibrated to published competition statistics, CMD achieves a projected mean Equal Error Rate (EER) of 1.95%, comparable to the Minutia Cylinder-Code (MCC, 1.91%) while requiring only 42 KB Flash and 8 KB base SRAM. On a simulated Cortex-M4 at 168 MHz, 1:100 identification completes in 6.9 ms, representing a 68x projected speedup over Bozorth3. These results suggest that competitive fingerprint matching is feasible on resource-constrained platforms without cloud offloading, enabling on-device authentication for edge deployments.

Keywords

Fingerprint Matching; Compact Minutiae Descriptor; Resource-Constrained Microcontrollers; Fixed-Point Arithmetic; Hierarchical Indexing; Embedded Biometric Authentication

References

[1] D. Maltoni, D. Maio, A. K. Jain, S. Prabhakar. Handbook of Fingerprint Recognition. Springer, 2009. [2] ARM Ltd. ARM Cortex-M4 Technical Reference Manual. ARM DDI 0439D, 2015. [3] A. K. Jain, A. Ross, S. Prabhakar. An introduction to biometric recognition. IEEE Transactions on Circuits and Systems for Video Technology, 14(1): 4-20, 2004. [4] P. Warden, D. Situnayake. TinyML: Machine Learning with TensorFlow Lite on Arduino and Ultra-Low-Power Microcontrollers. O'Reilly Media, 2019. [5] R. David, J. Duke, A. Jain, V. J. Reddi, N. Jeffries, J. Li, N. Kreber, I. Nappier, M. Natraj, T. Wang, P. Warden, R. Rhodes. TensorFlow Lite Micro: Embedded Machine Learning for TinyML Systems. Proceedings of Machine Learning and Systems, 3: 800-811, 2021. [6] C. I. Watson, M. D. Garris, E. Tabassi, C. L. Wilson, R. M. McCabe, S. Janet, K. Ko. User's Guide to NIST Biometric Image Software (NBIS). NIST Interagency Report 7392, 2007. [7] X. Jiang, W. Y. Yau. Fingerprint minutiae matching based on the local and global structures. Proceedings of the 15th International Conference on Pattern Recognition (ICPR), 2: 1038-1041, 2000. [8] R. Cappelli, M. Ferrara, D. Maltoni. Minutia Cylinder-Code: A New Representation and Matching Technique for Fingerprint Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(12): 2128-2141, 2010. [9] Neurotechnology. VeriFinger SDK Documentation. Available at: https://www.neurotechnology.com/verifinger.html, 2023. [10] D. Maio, D. Maltoni, R. Cappelli, J. L. Wayman, A. K. Jain. FVC2000: Fingerprint Verification Competition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(3): 402-412, 2002. [11] D. Maio, D. Maltoni, R. Cappelli, J. L. Wayman, A. K. Jain. FVC2002: Second Fingerprint Verification Competition. Proceedings of the 16th International Conference on Pattern Recognition (ICPR), 3: 811-814, 2002. [12] D. Maio, D. Maltoni, R. Cappelli, J. L. Wayman, A. K. Jain. FVC2004: Third Fingerprint Verification Competition. Biometric Authentication (ICBA), Lecture Notes in Computer Science 3072: 1-7, 2004. [13] N. K. Ratha, K. Karu, S. Chen, A. K. Jain. A Real-Time Matching System for Large Fingerprint Databases. IEEE Transactions on Pattern Analysis and Machine Intelligence, 18(8): 799-813, 1996. [14] M. Ferrara, D. Maltoni, R. Cappelli. Noninvertible Minutia Cylinder-Code Representation. IEEE Transactions on Information Forensics and Security, 7(6): 1727-1737, 2012. [15] Z. He, J. Zhang, L. Pang, E. Liu. PFVNet: A Partial Fingerprint Verification Network Learned From Large Fingerprint Matching. IEEE Transactions on Information Forensics and Security, 17: 3706-3719, 2022.