Pengenalan Sidik Jari Manusia Terdistorsi Menggunakan Algoritma Sift Based Minutia Descriptor (smd)
DOI:
https://doi.org/10.34818/eoe.v7i2.12379Abstract
Abstrak Pengenalan identitas seseorang sudah semakin berkembang, salah satunya pada identifikasi sidik jari. Hal tersebut digunakan sebagai upaya mengamankan data yang dimiliki melalui pengenalan identitas, agar orang lain tidak sembarangan mengakses data tersebut. Dalam penerapannya, sidik jari dilakukan oleh orang yang memiliki jari normal. Namun, orang yang memiliki jari tidak normal atau jari yang terdistorsi memiliki kesulitan untuk menggunakan sidik jari. Oleh karena itu, sidik jari yang terdistorsi dapat di akses apabila sistem diberikan perintah untuk dapat mendeteksi sidik jari yang terdistorsi. Tugas akhir ini membahas mengenai pengenalan sidik jari baik jari yang normal maupun jari yang terdistorsi (kulit kering, kulit pecah-pecah, dan kulit berminyak) dengan metode SIFT based Minutiae Descriptor (SMD) dan metode Brute Force Matcher (BF Matcher). Hasil pengujian menunjukkan sistem pengenalan sidik jari terdistorsi dengan menggunakan metode Algoritma SIFT Based Minutia Deskriptor (SMD) dan Brute Force Matcher pada kondisi ideal dengan tingkat akurasi sebesar 80.42%. Sistem dapat mengenali sidik jari terdistorsi dengan rata-rata lama waktu pengenalan citra sidik jari dengan respon time sebesar 13.58 detik per subyek. Kata kunci : BFMatcher. fingerprint, sidik jari terdistorsi, SIFT based Minutiae Descriptor. Abstract Recognition of a person's identity has increasingly developed, one of which is on fingerprint identification. This is used as an effort to secure data held through identity recognition, so that other people do not carelessly access the data. In its application, fingerprints are carried out by people who have normal fingers. However, people who have abnormal fingers or distorted fingers have difficulty using fingerprints. Therefore, a distorted fingerprint can be accessed if the system is given a command to detect a distorted fingerprint. This final project discusses the introduction of fingerprints of both normal and distorted fingers (dry skin, cracked skin, and oily skin) with the SIFT-based Minutiae Descriptor (SMD) method and the Brute Force Matching (BF Matcher) method. The test results show a distorted fingerprint recognition system using the SIFT Based Minutia Descriptor (SMD) Algorithm and Brute Force Matching in ideal conditions with an accuracy level of 80.42%. The system can recognize a distorted fingerprint with an average time of fingerprint image recognition with a response time of 13.58 seconds per subject. Keywords: Abnormal fingerprint, BFMatcher, fingerprint, SIFT based Minutia DescriptorDownloads
References
[1] R. Zhou, D. Zhong, and J. Han, “Fingerprint identification using SIFT-based minutia descriptors and improved all descriptor-pair matching,” Sensors (Switzerland), vol. 13, no. 3, pp. 3142–3156, 2013, doi: 10.3390/s130303142.
[2] H. A. A. Fahman Saeed, Muhammad Hussain, “Classification of Live Scanned Fingerprint using Dense SIFT based Ridge Orientation Feature,” Comput. Sci., pp. 5–8, 2018, [Online]. Available: file:///C:/Users/user/Music/PAPER TA/finger print in skin diseases/SIFT SMD/PAPER/sift based ridge orientation feature.pdf.
[3] S. Getzi, “Authentication Using Minutiae Based Fingerprint Matching Scheme for Smart Phones,” Int. J. Comput. Sci. Inf. Technol., vol. 5, no. 3, pp. 2937–2939, 2014.
[4] X. Si, S. Member, and J. Feng, “Detection and Rectification of Distorted Fingerprints.pdf,” vol. 37, no. 3, pp. 555–568, 2015.
[5] A. L. PRASASTI, B. IRAWAN, S. E. FAJRI, A. RENDIKA, and S. HADIYOSO, “Perbandingan Ekstraksi Fitur dan Proses Matching pada Autentikasi Sidik Jari Manusia,” ELKOMIKA J. Tek. Energi Elektr. Tek. Telekomun. Tek. Elektron., vol. 8, no. 1, p. 95, 2020, doi: 10.26760/elkomika.v8i1.95.
[6] G. S. Badrinath and P. Gupta, “Fingerprint Verification Using SIFT Features,” 2008 1st Int. Work. Image Process. Theory, Tools Appl. IPTA 2008, 2008, doi: 10.1109/IPTA.2008.4743763.
[7] R. Zhou, S. W. Sin, D. Li, T. Isshiki, and H. Kunieda, “Adaptive SIFT-based algorithm for specific fingerprint verification,” 2011 Int. Conf. Hand-Based Biometrics, ICHB 2011 - Proc., pp. 41–46, 2011, doi: 10.1109/ICHB.2011.6094354.
[8] M. Yamazaki, D. Li, T. Isshiki, and H. Kunieda, “SIFT-based algorithm for fingerprint authentication on smartphone,” 2015 6th Int. Conf. Inf. Commun. Technol. Embed. Syst. IC-ICTES 2015, pp. 4–8, 2015, doi: 10.1109/ICTEmSys.2015.7110836.
[9] A. N. D. Soetarmono, “Identifikasi Sidik Jari Dengan Menggunakan Struktur Minutia,” Teknika, vol. 1, no. 1, pp. 36–46, 2012, doi: 10.34148/teknika.v1i1.5.
[10] N. A. Nugraha, B. Irawan, and A. L. Prasasti, “Singapore Dollar Recognition Using ORB Feature Based on Android,” Proc. - 2018 Int. Conf. Control. Electron. Renew. Energy Commun. ICCEREC 2018, no. August 2019, pp. 142–148, 2018, doi: 10.1109/ICCEREC.2018.8711993.
[11] M. Rizky Adhiguna, B. Irawan, and A. Luhur Prasasti, “Design of Foreign Currency Recognition Application using Scale Invariant Feature Transform (SIFT) Method based on Android (Case Study: Singapore Dollar),” J. Eng. Appl. Sci., vol. 14, no. 19, pp. 6991–6997, 2019, doi: 10.36478/jeasci.2019.6991.6997.
[12] R. J, K. B. Raja, and V. K. R, “Fingerprint Recognition Using Minutia Score Matching,” vol. 1, no. 2, pp. 35–42, 2010, [Online]. Available: http://arxiv.org/abs/1001.4186.
[13] J. Abraham, P. Kwan, and J. Gao, “Fingerprint Matching using A Hybrid Shape and Orientation Descriptor,” 2011.
[14] S. Prabhakar, S. Pankanti, and A. K. Jain, “Biometric recognition: Security and privacy concerns,” IEEE Secur. Priv., vol. 1, no. 2, pp. 33–42, 2003, doi: 10.1109/MSECP.2003.1193209.
[15] M. Koeshardianto, “Pencocokan Obyek Wajah Menggunakan Metode Sift ( Scale Invariant Feature Transform ),” Nero, vol. 1, no. 1, pp. 53–59, 2014.
[16] A. Priadana, P. Studi, T. Informatika, U. Jenderal, and A. Yani, “Abstrak,” Anal. PENGARUH UKURAN CITRA Has. RESIZING TERHADAP JUMLAH KEYPOINT Has. EKSTRAKSI CIRI PADA Metod. Sift DAN SURF, vol. 11, pp. 9–18, 2018.
[17] A. P. Wicaksana, “Algoritma Brute Force dalam Pattern Matching pada Aplikasi Pendeteksian Potongan Citra,” 2013.
[18] N. Antony and B. R. Devassy, “Implementation of Image/Video Copy- Move Forgery Detection Using Brute-Force Matching,” Proc. 2nd Int. Conf. Trends Electron. Informatics, ICOEI 2018, no. Icoei, pp. 1085–1090, 2018, doi: 10.1109/ICOEI.2018.8553953.



