Klasifikasi Pola Sidik Jari Arch, Loop, dan Whorl Menggunakan Kombinasi Fitur Histogram of Oriented Gradients (HOG) dan Local Binary Pattern (LBP) dengan Support Vector Machine (SVM)

Rizal Parghani, Abdul Fadlil, Tole Sutikno

Abstract

Klasifikasi pola sidik jari ke dalam kategori struktural sebelum pencocokan minutiae membantu menyederhanakan sistem verifikasi identitas. Meskipun model deep learning seperti Convolutional Neural Network mampu mencapai akurasi tinggi, pendekatan tersebut umumnya memerlukan dataset besar dan sumber daya komputasi besar, sehingga mendorong eksplorasi alternatif berbasis fitur handcrafted yang lebih ringan. Penelitian ini mengusulkan model klasifikasi pola sidik jari yang menggabungkan deskriptor Histogram of Oriented Gradients (HOG) dan Local Binary Pattern (LBP), diklasifikasikan menggunakan Support Vector Machine (SVM) berkernel Radial Basis Function (RBF). Sebanyak 2.401 citra sidik jari dari repositori publik Kaggle digunakan, mencakup tiga kelas pola: Arch, Loop, dan Whorl. Setelah konversi grayscale, resize ke 128×128 piksel, dan peningkatan kontras CLAHE, citra dibagi menjadi 1.679 data latih, 479 data validasi, dan 243 data uji. Vektor fitur gabungan HOG-LBP berdimensi 8.110 distandardisasi sebelum melatih SVM, dengan hyperparameter dioptimalkan melalui grid search pada data validasi. Konfigurasi terbaik (C = 1, gamma = 0,001, kernel RBF) selanjutnya digunakan untuk menghasilkan akurasi uji sebesar 89,71% dan weighted average F1-score sebesar 89,75%. Whorl mencatatkan F1-score tertinggi (91,82%), sedangkan Arch mencatatkan recall terendah (88,89%), terutama akibat kesalahan klasifikasi dengan kelas Loop. Hasil ini menunjukkan bahwa kombinasi HOG-LBP-SVM merupakan solusi yang efisien secara komputasi dan kompetitif untuk klasifikasi pola sidik jari, meskipun penyempurnaan lebih lanjut seperti reduksi dimensi dan validasi silang k-fold masih berpotensi meningkatkan kemampuan diskriminasi model pada kelas dengan kemiripan struktural.

Keywords

klasifikasi sidik jari; Histogram of Oriented Gradients; Local Binary Pattern; Support Vector Machine; fusi fitur

Full Text:

PDF

References

Alhijaj, J. A., & Khudeyer, R. S. (2023). Integration of EfficientNetB0 and machine learning for fingerprint classification. Informatica (Slovenia), 47. https://doi.org/10.31449/inf.v47i5.4724

Aliffiyah, P. J., & Pratiwi, N. (2025). Deteksi tipe sidik jari untuk mengenali kepribadian menggunakan metode Support Vector Machine (SVM). METIK Jurnal, 9(2), 375–384. https://doi.org/10.47002/metik.v9i2.1073

Aljafary, G. H., & Hussian, A. (2025). Deep convolutional neural networks for fingerprint classification. Journal of Sana'a University for Applied Sciences and Technology. https://doi.org/10.59628/jast.v3i5.1831

Alshardan, A., Kumar, A., Alghamdi, M., Maashi, M., Alahmari, S., Alharbi, A. A. K., Almukadi, W., & Alzahrani, Y. (2024). Multimodal biometric identification: Leveraging convolutional neural network (CNN) Archhitectures and fusion techniques with fingerprint and finger vein data. PeerJ Computer Science, 10. https://doi.org/10.7717/peerj-cs.2440

Amadu, N., Douamba, F. W., & Umar, M. I. (2024). Fingerprint recognition based on convolutional neural network. In 2024 5th International Conference on Artificial Intelligence and Computer Engineering (ICAICE) (pp. 303–309). https://doi.org/10.1109/icaice63571.2024.10864270

Avuçlu, E., & Sarı, F. (2025). Handcrafted feature pipelines for image classification: A comparative study of HOG, LBP, and FFT within a transfer-learning-style workflow. Aksaray University Journal of Science and Engineering. https://doi.org/10.29002/asujse.1813481

Ayyappa, M. (2025). Fingerprint recognition using convolution neural network. International Journal of Scientific Research in Engineering and Management. https://doi.org/10.55041/ijsrem49476

Badawi, A., Mahfouz, M., Tadross, R., & Jantz, R. (2024). Fingerprint-based gender classification (pp. 41–46).

Barve, P. S., Narayanrao, M. P., Singh, D., Venkadeshwaran, K., Yuvaraj, K., & Nagpal, M. (2025). Decision-oriented image feature extraction using local binary patterns and histograms of oriented gradients. In 2025 International Conference on Decision Aid Sciences and Applications (DASA) (pp. 487–492). https://doi.org/10.1109/dasa68193.2025.11498774

Bhilavade, M. B., Shivaprakasha, K. S., Patil, M., Admuthe, L., & Magdum, A. N. (2024). Fingerprint reconstruction: Convolutional neural network based approach to improve fingerprint recognition. In 2024 2nd World Conference on Communication & Computing (WCONF) (pp. 1–6). https://doi.org/10.1109/wconf61366.2024.10692122

Cheng, G., Chen, J., Wei, Y., Chen, S., & Pan, Z. (2023). A coal gangue identification method based on HOG combined with LBP features and improved support vector machine. Symmetry, 15, 202. https://doi.org/10.3390/sym15010202

Ding, S., Shi, S., & Jia, W. (2020). Research on fingerprint classification based on twin support vector machine. IET Image Processing, 14(2), 231–235. https://doi.org/10.1049/iet-ipr.2018.5977

Efrizoni, L., Armoogum, S., & Zakaria, M. Z. (2024). Deep learning innovations in fingerprint recognition: A comparative study of model efficiencies. International Journal of Advances in Artificial Intelligence and Machine Learning. https://doi.org/10.58723/ijaaiml.v1i1.294

Garg, R., Singh, G., Singh, A., & Singh, M. (2024). Fingerprint recognition using convolution neural network with inversion and augmented techniques. Systems and Soft Computing. https://doi.org/10.1016/j.sasc.2024.200106

Hakim, L., & Hendro. (2020). Penentuan tes kepribadian calon mahasiswa berdasarkan sidik jari menggunakan Minutie dan Support Vector Machine. Journal of Applied Informatics and Computing (JAIC), 4(1), 28–32. http://jurnal.polibatam.ac.id/index.php/JAIC

Imanda, F., Setianingsih, C., & Paryasto, M. W. (2022). Deteksi kepribadian anak melalui sidik jari menggunakan metode Support Vector Machine. e-Proceeding of Engineering, 9(3), 1040–1046.

J, P., & Patil, P. G. A. (2025). Fingerprint biometric recognition using DABC and tanh-based fuzzy activated neural network. In 2025 International Conference on Transformative Computing Technologies (ICTCT) (pp. 207–214). https://doi.org/10.1109/ictct69201.2025.00049

Kothadiya, D. R., Bhatt, C. M., Soni, D., Gadhe, K., Patel, S. B., Bruno, A., & Mazzeo, P. (2023). Enhancing fingerprint liveness detection accuracy using deep learning: A comprehensive study and novel approach. Journal of Imaging, 9. https://doi.org/10.3390/jimaging9080158

Liu, H., Jia, X., Su, C., Yang, H., & Li, C. (2023). Tire appearance defect detection method via combining HOG and LBP features. https://doi.org/10.3389/fphy.2022.1099261

Long, B., Xiao, Y., Chen, J., Xiao, H., & Hu, C. (2025). A new fingerprint recognition algorithm based on RF-CNN. In 2025 IEEE International Conference on Teaching, Assessment, and Learning for Engineering (TALE) (pp. 1–8). https://doi.org/10.1109/tale66047.2025.11346581

Mahmood, S. H., Farhan, A. K., & El-Kenawy, E. M. (2023). A proposed model for fingerprint recognition based on convolutional neural networks. In 6th Smart Cities Symposium (SCS 2022). https://doi.org/10.1049/icp.2023.0572

Mahmoud, A., Awad, W. A., Behery, G., Abouhawwash, M., Masud, M., Aljuaid, H., & Ebada, A. (2023). An automatic deep neural network model for fingerprint classification. Intelligent Automation & Soft Computing, 36, 2007–2023. https://doi.org/10.32604/iasc.2023.031692

Meiramkhanov, T., & Tleubayeva, A. (2024). Enhancing fingerprint recognition systems: Comparative analysis of biometric authentication algorithms and techniques for improved accuracy and reliability. ArXiv, abs/2412.14404. https://doi.org/10.48550/arxiv.2412.14404

P. N. R., M. D., N. A., & Rao, A. S. (2025). A new approach utilizing DTCWT for feature extraction and ANN for classification to improve fingerprint recognition. Engineering Research Express, 7. https://doi.org/10.1088/2631-8695/ada667

Rachel, J., & Devarasan, E. (2025). Robust contactless fingerprint authentication using dolphin optimization and SVM hybridization. Frontiers in Big Data, 8. https://doi.org/10.3389/fdata.2025.1641714

Riaz, I., Ali, A. N., Ibrahim, H., & Huqqani, I. (2024). Biometric classification system for dorsal finger creases utilizing multi-block circular shift combination local binary pattern. International Journal of Electrical and Computer Engineering (IJECE). https://doi.org/10.11591/ijece.v14i5.pp5234-5243

Sen, A., Maiti, G., Parida, B., Mishra, B. P., Arya, M., & Bondar, D. I. (2025). Feature engineering is not dead: Reviving classical machine learning with entropy, HOG, and LBP feature fusion for image classification. ArXiv, abs/2507.13772. https://doi.org/10.48550/arxiv.2507.13772

Submitter, I. C., Batra, S., & M, G. (2026). Fingerprint recognition and matching using K-Nearest Neighbors. SSRN Electronic Journal. https://doi.org/10.2139/ssrn.6558998

Sutikno, Sugiharto, A., Kusumaningrum, R., & Wibawa, H. A. (2025). Combination of HAAR, HOG, and LBP descriptors for enhanced classification of moving objects and motorcyclists wearing helmets. Engineering, Technology & Applied Science Research. https://doi.org/10.48084/etasr.10677

baracuda0118. (n.d.). NIST DB4 - Fingerprint Pattern [Data set]. Kaggle. https://www.kaggle.com/datasets/baracuda0118/nist-db4-fingerprint-pattern

DOI: https://doi.org/10.31284/j.integer.2026.v11i2.9286

Refbacks

  • There are currently no refbacks.