Önceden Eğitilmiş Çeşitli Derin Sinir Ağları Kullanarak Parmak İzi Örüntü Sınıflandırma

Öz

Biyometri teknolojisi, kişisel kimlik tespiti gibi güvenlik konuları açısından oldukça önemlidir. Göz-iris tanıma, yüz tanıma ve damar örüntüsü tanıma gibi biyometrik teknoloji ile ilgili birçok çözüm sunulmuştur. Dahası, günümüzün en önemli kimlik doğrulama yöntemlerinden biri parmak izi tanımadır. Her parmak izinin kendine özgü sırt, çukur, delta ve çekirdek model örüntüsü vardır. Bu örüntüler lasso(ilmek), ark(yay) ve wirbel gibi benzersiz parmak izi tiplerini oluşturur. Parmak izi paterni tanıma sorunu, eşleştirme sürecini hızlandırmak için çok önemli bir ön adımdır. Bu nedenle, özellikle büyük parmak izi veritabanları için her zaman doğru bir örüntü tanıma yöntemine ihtiyaç vardır. Geleneksel yöntemlerin yanı sıra son zamanlarda parmak izi örüntü tanıma amacıyla daha çok CNN kullanılmaktadır ve literatürde yüksek tanıma oranlarına ulaşan birçok çalışma bulunmaktadır. Bu çalışmada, tanıma oranlarını artırmak için önceden egitilmis Xception ve NasNetLarge CNN mimarilerini kullanarak parmak izi sınıflandırmasına yönelik otomatik bir teknik öneriyoruz. NIST Özel veritabanı 4'ü kullanarak deneyler yapildi ve dört kategori için: yay, sağ lasso, sol lasso ve wirbel, şu ana kadarki en iyi puan olan %97.3 ve % 98,5 tanınma oranlarina ulaştık. Ayrıca model, yay ve fitilli yay iki ayrı sınıfa ayrılarakta test edilmiş ve 5 sınıf için % 91,5 ve %90.2 tanınma oranına ulaşılmıştır.

Anahtar Kelimeler

• Parmak izi tanıma sistemleri
• derin ogrenme
• evrisimli sinir agi
• oruntu tanima
• Henry siniflandirma sistemi

Fingerprint Pattern Classification by Using Various Pre-Trained Deep Neural Networks

Öz

Biometrics technology is very important in terms of security issues like the identification of personal identity. Many solutions have been offered regarding biometric technology such as eyes-iris recognition, face recognition and vein pattern recognition. Moreover, one of the today’s most important authentication methods is fingerprint recognition. Each fingerprint has different pattern of ridges, valleys, deltas and cores. Those pattern types indicate unique fingerprints such as arch, left loop, right loop, tent arch and whorl. The issue of fingerprint pattern recognition is a crucial prior step to speed up the matching process of fingerprint recognition systems. Therefore, an accurate pattern recognition method is always needed, especially for large fingerprint databases. Besides traditional methods, recently, CNN is mostly used for fingerprint pattern recognition and there are many studies in the literature which achieve high recognition rates. In this study, we propose an automated tecnique toward fingerprint classification using various pretrained CNNs Xception and NasNetLarge in order to increase recognition rates. We performed experiments using NIST Special database 4 and we achieved 97.3 98.5% recognition rates respectively, which are the best scores up to now, for four categories: arch, right loop, left loop and whorl. The models was also tested into 5 fingerprint classes which arch and tented arch were seperated as two different classes with the recognition rate of 91.5% and 90.2% respectively.

Anahtar Kelimeler

• Fingerprint recognition systems
• Deep learning
• Convolutional Neural Network
• Pattern recognition
• Henry classification system

Kaynakça

1. Shrestha and B. K. Malla, “Study of Fingerprint Patterns in Population of a Community”,J Nepal Med Assoc, vol. 57, no. 219, Oct. 2019.
2. J. Y. Kang, J. S. Lee, J. H. Lee, S. M. Kong, D. H. Kim, and S. B. Lee, “A study on the dynamic binary fingerprint recognition method using artificial intelligence,” Journal of Korean Institute of Intelligent Systems, vol. 13, no. 1, pp. 57-62, 2003. https://doi.org/10.5391/JKIIS.2003.13.1.057
3. W. J. Kim, C. G. Lee, Y. T. Kim, and S. B. Lee, “Implementation of embedded system and finger print identification using ART2,” Proceedings of KIFS Spring Conference, vol. 16, no. 1, pp. 90-93, 2006.
4. H. W. Jung and J. H. Lee, “Various quality fingerprint classification using the optimal stochastic models,” Journal of the Korea Society for Simulation, vol. 19, no. 1, pp. 143-151, 2010.
5. A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” in Proceeding of Neural Information Processing Systems Conference and Workshop, Lake Tahoe, NV, 2012, pp. 1097-1105
6. R.Wang, C. Han, Y.Wu, and T. Guo, “Fingerprint classification based on depth neural network,” 2014, Available: https://arxiv.org/abs/1409.5188
7. J. S. Bae, S. K. Oh, and H. K. Kim, “Design of fingerprints identification based on RBFNN using image processing techniques,” The transactions of The Korean Institute of Electrical Engineers, vol. 65, no. 6, pp. 1060-1069, 2016. https://doi.org/10.5370/KIEE.2016.65. 6.1060
8. D. Peralta, I. Triguero, S. Garcia, Y. Saeys, J. M. Benitez, and F. Herrera, “On the use of convolutional neural networks for robust classification of multiple fingerprint captures,” 2017, Available: https://arxiv.org/abs/1703.

9. H. I. Kim, D. S. An, and C. W. Ryu, “Fingerprint recognition,” in Proceeding of the Biometric Consortium Conference, 2001.
10. Pretrained CNN: https://www.mathworks.com/help/deeplearning/ug/pretrained-convolutional-neural-networks.html. Accessed on: 02.03.2021
11. Candela G T, Grother P J, Watson C I, et al. PCASYS-A pattern-level classification automation system for fingerprints[J]. NIST technical report NISTIR, 1995, 5647.
12. Karu K, Jain A K. Fingerprint classification[J]. Pattern recognition, 1996, 29(3): 389-404.
13. Jain A K, Minut S. Hierarchical kernel fitting for fingerprint classification and alignment[C]//Pattern Recognition, 2002. Proceedings. 16th International Conference on. IEEE, 2002, 2: 469-473.
14. Yao Y, Frasconi P, Pontil M. Fingerprint classification with combinations of support vector machines[C]//Audio-and Video-Based Biometric Person Authentication. Springer Berlin Heidelberg, 2001: 253-258.
15. Zhang Q, Yan H. Fingerprint classification based on extraction and analysis of singularities and pseudo ridges[J]. Pattern Recognition, 2004, 37(11): 2233-2243.
16. Liu M. Fingerprint Classification Based on Singularities[C]//Pattern Recognition, 2009. CCPR 2009. Chinese Conference on. IEEE, 2009: 1-5.
17. Ruxin Wang, Congying Han and Tiande Guo, "A novel fingerprint classification method based on deep learning," 2016 23rd International Conference on Pattern Recognition (ICPR), Cancun, 2016, pp. 931-936, doi: 10.1109/ICPR.2016.7899755.
18. Jeon, Wang-Su & Rhee, Sang-Yong. (2017). Fingerprint Pattern Classification Using Convolution Neural Network. International Journal of Fuzzy Logic and Intelligent Systems. 17. 170-176. 10.5391/IJFIS.2017.17.3.170.