Optimization of VGG-16 Accuracy for Fingerprint Pattern Imager Classification

Agus Andreansyah; Julian Supardi

Authors

Agus Andreansyah University of Sriwijaya
Julian Supardi Department of Master of Computer Science, University of Sriwijaya

Keywords:

Fingerprint, Optimization, Classification, VGG-16. CNN

Abstract

Fingerprint is a unique biometric identity commonly used as evidence in court. However, its quality can decline due to external factors such as uneven surfaces, weather conditions, or distortion. The dataset used in this study is FVC2000. Convolutional Neural Networks (CNN) were applied for fingerprint image enhancement and classification, focusing on patterns such as whorl, arch, radial loop, ulnar loop, and twinted loop. This research optimized the VGG-16 model by adding several hyperparameters. The results showed the highest accuracy of 100% on the testing data with a learning rate of 0.0001, using 50 epochs and a training-to-validation data split ratio of 80%:10% from a total of 400 fingerprint image pattern data. These findings demonstrate that the VGG-16 model successfully classified fingerprint images with optimal performance, contributing significantly to the development of CNN-based fingerprint classification systems.

References

Albahli, Saleh, 2020, Detection of Coronavirus Disease From X-Ray Images Using Deep Learning and Transfer Learning Algorithms, Journal of X-Ray Science and Technology, Saudi arabia.

Andreansyah, Agus, Rika F, M. Jumnahdi., 2019, Pengenalan Pola Sidik Jari Menggunakan Multi-Class Support Vector Machine, Jurnal Elkha, pp. 79-84.

Andreea Monica Dinca, Lazarescu. dkk., 2022, A Fingerprint Matching Algorithm Using the Combination of Edge Features and Convolution Neural Network, MDPI Inventions, Romania, Pp. 39.

Arnita, Faridawaty, dkk, 2022, Computer Vision dan Pengolahan Citra Digital, ISBN 978-623-8230-27-3, Pustaka Aksara.

B. Bakhshi dan H, Veisi, 2017, End to End Fingerprint Verification Based on Convolutional Neural Network, in 27th Iranian Conference on Electrical Engineering (ICEE2019), Tehran, pp. 1994 -1998.

Cholussodin, Imam et al, 2020, Buku Ajar AI, Machine Learning & Deep Learning, Filkom, Universitas Brawijaya.

Cimtay, Yucel et al, 2021, Fingerprint Pattern Classification by Using Various Pre-Trained Deep Learning Networks, European Journal of Science and Technology (EJOSAT), Special Issue 24, pp. 258-261.

Emil Naf’an, et al, 2022, Dasar-dasar Deep Learning dan Contoh Aplikasinya, Penerbit: CV. Mitra Cendekia Media, Sumatra Barat.

Garg, Reena et al, 2024, Fingerprint Recognition Using Convolution Neural Network with intevesion and augmented techniques, Journal Elsevier, India.

Hadaris, Arisy Nabawi, 2020, Modul Daktiloskopi antara Tantangan, Peluang dan Harapan, Badan Pengembangan Sumber Daya Manusia Hukum dan Hak Asasi Mnausia Kementerian Hukum dan Hak Asasi Manusia Republik Indonesia, ISBN 978-623-6869-37-6, Percetakan Pohon Cahaya.

Hidayatullah, priyanto., 2023, Buku Sakti Deep Learning, Penerbit Stunning Vision AI Academy.

Hirsi Mohamed, 2021, Fingerprint Classification Using Deep Convolutional Neural Network, ISSN: 2329-1613, Journal of Electrical and Electronic Engineering, Turkey.

Indonesia, Undang-Undang tentang Kitab Undang-Undang Hukum Acara Pidana, UU No. 8 Tahun 1981, LN No. 76 Tahun 1981, Psl. 184.

Irsyad, Rahadian, 2018, Penggunaan Python Web Framework Flask untuk Pemula, Laboratorium Telematika, Institut Teknologi Bandung,

Liyananta, Mohammad et al, 2024, Klasifikasi Tumor Otak Menggunakan CNN dengan Arsitektur Resnet 50, Prosiding Seminar Nasional Teknologi dan Sains, Universitas Nusantara PGRI Kediri.

M. Galar et al, 2015, A Survey of Fingerprint Classification Part II: Experimental Analysis and ensemble proposal, Knowledge Based Systems, Vol. 81, pp. 98-116.

Purba, Nelvitia., Amran Basri, dkk., 2017, Kejahatan dan Penjahat dari Aspek Kriminologi, Mahara Publishing, ISBN 978-602-6914-78-1, Tanggerang, Banten.

Putra, Jan Wira Gotama, 2020, Pengenalan Konsep Pembelajaran Mesindan Deep Learning, wiragotama.github, Tokyo, Jepang.

Raharjo, Budi, 2022, Deep Learning dengan python, Penerbit: Yayasan Prima, ISBN: 978-623-5734-33-0, Semarang.

Ramesh Chandra Sahoo, dkk. 2019. Application of Deptwise Separable Convolutional Neural Network for Distorted Fingerprint Images, International Journal of control and automation. Vol. 12, No.6, pp. 448-455.

Sidik, Farih Maulana, 2024, 8 Kasus Pembunuhan Bikin Geger dalam Dua Pekan Terakhir, detiknews, diakses pada tanggan 8 Juni 2024 pada laman https://news.detik.com/berita/d-7334539/8-kasus-pembunuhan-bikin-geger-dalam-2-pekan-terakhir/1

Santoso, Joseph Teguh, 2022, Proyek Coding dengan Python, Penerbit: Yayasan Prima, ISBN: 978-623-5734-31-6, Semarang.

Satriawan, Akbar Muhammad dan Wijang, 2023, Klasifikasi Pengenalan Wajah untuk Mengetahui Jenis Kelamin Menggunakan Metode Convolutional Neural Network, Jurnal Algoritma, Vol. 4, No. 1, pp. 43-52.

Shrestha and B.K Malla, 2019, Study of Fingerprint Pattern in Population of a Community, J Nepal Med Assoc, Vol. 57 No. 219.

Supardi, Julian and Shi-Jinn Horng, 2019, Very Small Image Face Recognition Using Deep Convolutional Neural Network, Journal of Physisc: Conference Series 1196 (ICONISCSE).

Syarif Hartawan, Muhammad., Suhardjono, dkk., 2022, Digital Forensik, ARS Trainning,

Triwani, Pemeriksaan Dermatoglifi sebagai Alat Identifikasi dan Diagnostik, Fakultas Kedokteran, Universitas Sriwijaya, Palembang.