A Machine Learning Approach Facilitating Contactless and Contact-Based Fingerprint Recognition through Magnitude Spectrum

doi:10.23940/ijpe.26.06.p6.352361

Abstract

Abstract: Matching contactless fingerprint images with traditional contact-based impressions has become increasingly important, especially due to the COVID-19 pandemic. Contactless methods provide better hygiene and benefit from the availability of affordable mobile phones capable of capturing high-resolution fingerprints. Traditional minutiae-based matching techniques are susceptible to errors caused by false or missing minutiae points in low-quality images, emphasizing the need for alternative features. This study explores the magnitude spectrum, a feature derived from the Discrete Fourier Transform (DFT) for matching contactless and contact-based fingerprints. A 256-bin histogram of the magnitude spectrum is generated to estimate the correlation distance to distinguish genuine from imposter attempts. Using this dataset, a Support Vector Machine (SVM) model is carefully trained and tested through 10-fold cross-validation. The results demonstrate a high matching accuracy of 97.97%, with an Equal Error Rate (EER) of 2.02% and a Rank 1 accuracy of 93.38%. The SVM classifier also achieves 96.96% accuracy in differentiating between 'genuine' and 'imposter' classes.

Key words: magnitude spectrum, histogram feature vector, support vector machine, contactless fingerprint, contact-based fingerprint, cross-fingerprint verification

Payal Singh, Diwakar Agarwal, and Ajitesh Kumar. A Machine Learning Approach Facilitating Contactless and Contact-Based Fingerprint Recognition through Magnitude Spectrum [J]. Int J Performability Eng, 2026, 22(6): 352-361.

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

References

[1] Grosz S.A., Godbole A., andJain A.K., 2024. Mobile contactless palmprint recognition: use of multiscale, multimodel embeddings.IEEE Transactions on Information Forensics and Security, 19, pp. 8428-8440.
[2] Gonzalez-Soler L.J., Zyla K.M., Rathgeb C., andFischer D., 2024. Contactless hand biometrics for forensics: review and performance benchmark.EURASIP Journal on Image and Video Processing, 2024(1), 26.
[3] Pan Z., Duan Y., Guan X., Feng J., andZhou J., 2024. Latent fingerprint matching via dense minutia descriptor. In2024 IEEE International Joint Conference on Biometrics (IJCB), pp. 1-10.
[4] Calderon-Calderon M.D., Medina-Perez M.A., andMonroy R., 2025. Improving identification by removing obstructive minutiae from latent fingerprints.IEEE Access, 13, pp. 7968-7985.
[5] Byeon H., Seno M.E., Nimma D., Ramesh J.V.N., Zaidi A., AlGhamdi A., Keshta I., Soni M., andShabaz M., 2025. Privacy-preserving explainable AI enable federated learning-based denoising fingerprint recognition model.Image and Vision Computing, 154, 105420.
[6] Mader J., andLorünser T., 2024. Feasibility of privacy preserving minutiae-based fingerprint matching. ICISSP, 2024, 10th.
[7] Sharma D., andSelwal A., 2023. SFincBuster: spoofed fingerprint buster via incremental learning using leverage bagging classifier.Image and Vision Computing, 135, 104713.
[8] Adami B., Hosseinzadehketilateh M., andKarimian N., 2024. Contactless fingerprint biometric anti-spoofing: an unsupervised deep learning approach. In2024 IEEE International Joint Conference on Biometrics (IJCB), pp. 1-10.
[9] Vyas R., andKumar A., 2024. A collaborative approach using ridge-valley minutiae for more accurate contactless fingerprint matching. InInternational Conference on Pattern Recognition, pp. 273-287.
[10] Jin A.T.B., Ling D.N.C., andSong O.T., 2004. An efficient fingerprint verification system using integrated wavelet and fourier-mellin invariant transform. Image and Vision Computing,22(6), pp. 503-513.
[11] Taboga M.,Discrete Fourier transform - Spectra, https://www.statlect.com/matrix-algebra/discrete-Fourier-transform-amplitude-power-phase-spectrum, accessed on May 1, 2026.
[12] Lin C., andKumar A., 2018. Matching contactless and contact-based conventional fingerprint images for biometrics identification. IEEE Transactions on Image Processing,27(4), pp. 2008-2021.
[13] Singh S.P., Nishad D.K., andKhalid S., 2025. Enhancing fingerprint identification using fuzzy-ANN minutiae matching.Measurement: Sensors, 37, 101809.
[14] Mishra H.M., Jha A.K., Sikarwal P.K., Mirza S., Kumar M., andKaur D., 2024. Exploring the enabling technologies of contactless fingerprint reader. In2024 IEEE International Conference on Information Technology, Electronics and Intelligent Communication Systems (ICITEICS), pp. 1-6.
[15] Alotaibi A., Hussain M., andAboalsamh H.A., 2024. Cross-sensor fingerprint recognition using convolutional neural network and canonical correlation analysis.IEEE Access, 12, pp. 84738-84751.
[16] Pan Z., Duan Y., Feng J., andZhou J., 2024. Fixed-length dense descriptor for efficient fingerprint matching. In2024 IEEE International Workshop on Information Forensics and Security (WIFS), pp. 1-6.
[17] Birajadar P., Haria M., Kulkarni P., Gupta S., Joshi P., Singh B., andGadre V., 2019. Towards smartphone-based touchless fingerprint recognition.SāDhanā, 44(7), 161.
[18] Malhotra A., Sankaran A., Vatsa M., andSingh R., 2020. On matching finger-selfies using deep scattering networks. IEEE Transactions on Biometrics, Behavior, and Identity Science,2(4), pp. 350-362.
[19] Grosz S.A., Engelsma J.J., Liu E., andJain A.K., 2021. C2CL: contact to contactless fingerprint matching.IEEE Transactions on Information Forensics and Security, 17, pp. 196-210.
[20] Rajaram K., Amma N.B., andSelvakumar S., 2023. Convolutional neural network based children recognition system using contactless fingerprints. International Journal of Information Technology,15(5), pp. 2695-2705.
[21] Baghel V.S., andPrakash S., 2022. Generation of secure fingerprint template using DFT for consumer electronics devices. IEEE Transactions on Consumer Electronics,69(2), pp. 118-127.
[22] Parasnis G., Bhope R., Chokshi A., Jain V., Biswas A., Kumar D., Pateriya S., Anand V., Kanhangad V., andGadre V.M., 2024. Verifnet-a novel score fusion-based method leveraging wavelets with deep learning and minutiae matching for contactless fingerprint recognition. IEEE Transactions on Biometrics, Behavior, and Identity Science,7(3), pp. 344-353.
[23] Sanjay Gaikwad A., andMusande V.B., 2023. A novel fingerprint-based age group classification approach using DWT and DFT analysis. InInternational Conference on Image Processing and Capsule Networks, pp. 389-410.
[24] Siddiqui M., Iqbal S., AlHaqbani B., AlShammari B., Khan T., andRazzak I., 2024. A robust algorithm for contactless fingerprint enhancement and matching. In2024 International Conference on Digital Image Computing: Techniques and Applications (DICTA), pp. 214-220.
[25] Kaplesh P., Gupta A., Bansal D., Sofat S., andMittal A., 2025. Vision transformer for contactless fingerprint classification. Multimedia Tools and Applications,84(26), pp. 31239-31259.
[26] Ruzicka L., Kohn B., andHeitzinger C., 2025. TipSegNet: fingertip segmentation in contactless fingerprint imaging.Sensors, 25(6), 1824.
[27] Peddi S., Bandyopadhyay S., andSamanta D., 2025. G-msginet: A grouped multi-scale graph-involution network for contactless fingerprint recognition.Arxiv Preprint Arxiv:2505.08233.
[28] Liu F., Huang Y., Li Y., andWang Q., 2025. CrossFingerprint: A multi-level fusion network for 3D fingerprint verification.Neurocomputing, 648, 130706.
[29] Yun E.K., andCho S.B., 2006. Adaptive fingerprint image enhancement with fingerprint image quality analysis. Image and Vision Computing,24(1), pp. 101-110.
[30] Sharma R.P., andDey S., 2019. Two-stage quality adaptive fingerprint image enhancement using fuzzy C-means clustering based fingerprint quality analysis.Image and Vision Computing, 83, pp. 1-16.
[31] Nussbaumer H.J.,1981. The fast fourier transform. InFast Fourier Transform and Convolution Algorithms, pp. 80-111
[32] Park C.H., andPark H., 2005. Fingerprint classification using fast fourier transform and nonlinear discriminant analysis. Pattern Recognition,38(4), pp. 495-503.
[33] Spatial Frequency Domain, https://www.cs.auckland.ac.nz/courses/compsci773s1c/lectures/ImageProcessing-html/topic1.htm, accessed on May 1, 2026.
[34] OpenCV, Histogram Comparison, https://docs.opencv.org/3.4.20/d8/dc8/tutorial_histogram_comparison.html, accessed on May 1, 2026.
[35] Huang S., Cai N., Pacheco P.P., Narrandes S., Wang Y., andXu W., 2018. Applications of support vector machine (SVM) learning in cancer genomics. Cancer Genomics & Proteomics,15(1), pp. 41-51.
[36] Kuo B.C., Ho H.H., Li C.H., Hung C.C., andTaur J.S., 2013. A kernel-based feature selection method for SVM with RBF kernel for hyperspectral image classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,7(1), pp. 317-326.
[37] Vert J.P., Tsuda K., andSchölkopf B., 2004. A primer on kernel methods. InKernel Methods in Computational Biology, pp. 35-70.
[38] Yarlagadda S.M.,Understanding Sensitivity, Specificity, Precision, Recall, F1 Score, and Confusion Matrix in Binary Classification, https://saimanojyarlagadda.medium.com/understanding-sensitivity-specificity-precision-recall-f1-score-and-confusion-matrix-in-binary-495b66447621, accessed on May 1, 2026.
[39] OpenAI, OpenAI to acquire Neptune, https://openai.com/index/openai-to-acquire-neptune/, accessed on May 1, 2026.
[40] Veldhuis R.N., andRaja K., 2023. On the relation between ROC and CMC. IEEE Transactions on Biometrics, Behavior, and Identity Science,5(4), pp. 538-552.
[41] DeCann B., andRoss A., 2013. Relating roc and cmc curves via the biometric menagerie. In2013 IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems (BTAS), pp. 1-8.