Enhancing Fingerprint Recognition System by the Fused Edge Map

Article Sidebar

PDF
Published: Sep 29, 2025
Keywords:
Biometric identification Edge detecting Fingerprint recognition Fused Edge Map (FEM)

Main Article Content

Lwin Min Paing
Departmen of Electrical Engineering, Faculty of Engineering, Chulalongkorn University, Bangkok 10330, Thailand, Communications and Information Engineering (CIE), Bangkok 10330, Thailand
Charnchai Pluempitiwiriyawej
Departmen of Electrical Engineering, Faculty of Engineering, Chulalongkorn University, Bangkok 10330, Thailand, Communications and Information Engineering (CIE), Bangkok 10330, Thailand, Multmedia Data Analytics and Processing Research Unit, Bangkok 10330, Thailand
Lunchakorn Wuttisittikulkij
Departmen of Electrical Engineering, Faculty of Engineering, Chulalongkorn University, Bangkok 10330, Thailand, Holistic Health Care for All Research Group, Bangkok 10330, Thailand, Communications and Information Engineering (CIE), Bangkok 10330, Thailand

Abstract

Biometric identification technologies such as fingerprint, facial recognition, and iris or retina scans are widely integrated into modern identity verification systems, including smartphones, computers, and smart home access control. Among these, fingerprint recognition is one of the most extensively used methods due to the uniqueness of ridge patterns in individual fingerprints. In this paper, we propose a fingerprint matching system based on edge detection techniques. Specifically, we utilize three traditional edge detection operators—Canny, Prewitt, and Sobel—to extract edge features from fingerprint images. The proposed system involves four primary steps: image pre-processing, edge detection using the three operators, fusion of the resulting edge maps, and morphological processing to enhance edge features, followed by a decision-making process based on a matching threshold. We introduce a fusion strategy, Fused Edge Map (FEM), that combines the strengths of each operator to generate a more accurate edge representation. To evaluate FEM, we apply two fusion methods: Majority-based Fusion (MF) and Union-based Fusion (UF). Experimental results show that MF achieves a fingerprint matching accuracy of 92.82%, while UF outperforms all individual edge detectors and the MF method, achieving a matching accuracy of 96.25%.

Article Details

How to Cite
Lwin Min Paing, Charnchai Pluempitiwiriyawej, & Lunchakorn Wuttisittikulkij. (2025). Enhancing Fingerprint Recognition System by the Fused Edge Map. Science & Technology Asia, 30(3), 1–12. retrieved from https://ph02.tci-thaijo.org/index.php/SciTechAsia/article/view/261429
Issue
Vol.30 No.3 (July-September 2025)
Section
Articles
Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

References

Koong CS, Yang TI, Tseng CC. A user authentication scheme using physiological and behavioral biometrics for multitouch devices. Sci World J. 2014;2014:781234.

Rathod VJ, Iyer NC. A survey on fingerprint biometric recognition system. In: 2015 International Conference on Green Computing and Internet of Things (ICGCIoT). IEEE; 2015. p. 323-6.

Chitradevi B, Srimathi P. An overview on image processing techniques. Int J Innov Res Comput Commun Eng. 2014;2(11):6466-72.

Sun R, Lei T, Chen Q, Wang Z, Du X, Zhao W, et al. Survey of image edge detection. Front Signal Process. 2022;2:826967.

Altameemi HG, Ismael AA, Mehsen RS. Hough transform for distinctive edge detection to images in fingerprint recognition matching transformation. Webology. 2021;18(2).

Li X, Jiao H, Wang Y. Edge detection algorithm of cancer image based on deep learning. Bioengineered. 2020;11(1):693-707.

Pluempitiwiriyawej C. Image segmentation [lecture slides]. Bangkok: Chulalongkorn University; 2025 Feb [cited 2025 Apr 18].

Savant S. A review on edge detection techniques for image segmentation. Int J Comput Sci Inf Technol. 2014;4:5898-900.

Ziou D, Tabbone S. Edge detection techniques: an overview. Pattern Recognit Image Anal. 1998;8(4):537-59.

Canny J. A computational approach to edge detection. IEEE Trans Pattern Anal Mach Intell. 1986;PAMI-8(6):679-98.

Chanklan R, Chaiyakhan K, Hirunyawanakul A, Kerdprasop K, Kerdprasop N. Fingerprint recognition with edge detection and dimensionality reduction techniques. In: Proc 3rd Int Conf Ind Appl Eng. Japan; 2015.

Diarra M, Jean AK, Bakary BA, Médard KB. Study of deep learning methods for fingerprint recognition. Int J Recent Technol Eng. 2021;10(3):192-7.

Meiramkhanov T, Tleubayeva A. Enhancing fingerprint recognition systems: Comparative analysis of biometric authentication algorithms and techniques. arXiv preprint arXiv:2412.14404. 2024 Dec 18.

Li X, Xie M, Bin D. A fingerprint recognition method based on deep learning. In: Proc 8th Int Conf High Perform Compilation, Comput Commun. 2024. p. 87-91.

Garg R, Singh G, Singh A, Singh MP. Fingerprint recognition using convolution neural network with inversion and augmented techniques. Syst Soft Comput. 2024;6:200106.

Vaiwala VA. Recital analysis on various image edge detection techniques. Int J Res Anal Rev. 2015;2(4):725-9. Available from: https://www.ijrar.org/papers/IJRAR19D4-861.pdf

Shakadwipi AJ, Agarkar MP, Ahluwalia AM, Jain SP, Parakh A. Smart traffic control system by using image processing. IOSR J Comput Eng. 2020.

Nikolic M, Tuba E, Tuba M. Edge detection in medical ultrasound images using adjusted Canny edge detection algorithm. In: 24th Telecommunications Forum (TELFOR). IEEE; 2016. p. 1-4.

Shajeena J, Jarugula VK, Bindhu A, Kayalvizhi S. Utilizing convolutional neural networks for object recognition with image filtering and edge detection. In: 6th Int Conf Recent Trends Adv Comput (ICRTAC). IEEE; 2023. p. 784-9.

Dincă Lăzărescu AM, Moldovanu S, Moraru L. A fingerprint matching algorithm using the combination of edge features and convolution neural networks. Inventions. 2022;7(2):39.

Winarno E, Hadikurniawati W, Wibisono S, Septiarini A. Edge detection and grey level co-occurrence matrix algorithms for fingerprint identification. In: 2nd Int Conf Innov Creative Inf Technol (ICITech). IEEE; 2021. p. 30-4.

Liu TS, Liu RX, Ping-Zeng SW. Improved Canny algorithm for edge detection of core image. Open Autom Control Syst J. 2015;6(1):426-32.

Prewitt JM. Object enhancement and extraction. Picture Process Psychopictorics. 1970;10(1):15-9.

Yang L, Wu X, Zhao D, Li H, Zhai J. An improved Prewitt algorithm for edge detection based on noised image. In: 4th Int Congr Image Signal Process. IEEE; 2011. p. 1197-200.

Sobel I, Feldman G. A 3×3 isotropic gradient operator for image processing. Talk at Stanford Artificial Project. 1968;271-2.

Zhang CC, Fang JD. Edge detection based on improved Sobel operator. In: Int Conf Comput Eng Inf Syst. Atlantis Press; 2016. p. 129-32.

Shehu YI, Ruiz-Garcia A, Palade V, James A. Sokoto Coventry fingerprint dataset. arXiv preprint arXiv:1807.10609. 2018 Jul 24.

Zhang Y, Han X, Zhang H, Zhao L. Edge detection algorithm of image fusion based on improved Sobel operator. In: 3rd Inf Technol Mechatronics Eng Conf (ITOEC). IEEE; 2017. p. 457-61.

Singh H, Kaur M. Compound approach for digital image of Sobel, Canny and LoG edge detection techniques. Int J Adv Comput Eng Netw. 2015;3(8):51-4.

Jadeja M. Jaccard similarity made simple: A beginner’s guide to data comparison. Medium. 2022 Nov. Available from: https://mayurdhvajsinhjadeja.medium.com-/jaccard-similarity-34e2c15fb524

Pearson K. Note on regression and inheritance in the case of two parents. Proc R Soc Lond. 1895;58(347-52):240-2.

Wang Z, Bovik AC, Sheikh HR, Simoncelli EP. Image quality assessment: From error visibility to structural similarity. IEEE Trans Image Process. 2004;13(4):600-12.

The MathWorks Inc. corr2-2-D correlation coefficient. Image Processing Toolbox, R2024a; 2024.