A Novel Approach to Fingerprint Authentication Using Histogram Oriented Gradients for Feature Extraction and Machine Learning Convolution Neural Network for Classification

Year : 2023 | Volume :01 | Issue : 02 | Page : 1-12
By

Pradeep N.R,

Manohara T N,

Sreenivasa T V,

  1. Associate Professor, Department of Electrical Communication Engineering, Channabasaveshwara Institute of Technology, Gubbi, Tumakuru, Karnataka, India
  2. Assistant Professor, Department of Electrical Communication Engineering, Channabasaveshwara Institute of Technology, Gubbi, Tumakuru, Karnataka, India
  3. Assistant Professor, Department of Electrical Communication Engineering, Channabasaveshwara Institute of Technology, Gubbi, Tumakuru, Karnataka, India

Abstract

With applied biometrics, it is possible to identify a person by examining a feature vector of attributes derived from their physical and behaviour characteristics. In biometrics, fingerprints have become one of the most famous and well known techniques of identification and authentication. In light of technological advancements and safety, fingerprint recognition has been successfully used in a variety of Civil, Defence, and Commercial applications for more than a decade. The use of fingerprints for signature applications started in the second millennium and studies have been conducted on the different aspects as well as attributes of fingerprints over the past decade. In addition to CNN for deep learning, this study introduces a Histogram Oriented Gradient for feature extraction. Histogram equalisation, filter enhancement, and fingerprint thinning are a few of the preprocessing strategies for obtaining fingerprint features. A deep convolutional neural network algorithm has been created for the purpose of classifying preprocessed fingerprints. Compared to deep learning networks, HOG-based CNN is extremely efficient. In addition, CNN is challenged by its inability to rotate. Despite the fact that CNN has already been investigated, we propose a novel and simple HOG-based CNN that generates highly valued data efficacy and is rotation-invariant. For validation within the database, 64 epochs achieved 99.47% accuracy, against 100% training accuracy. A validation accuracy of 4.33% was achieved for an outside database with a training accuracy of 6.33%. In comparison with contemporary machine learning algorithms, the accuracy achieved in this work is considerably higher.

Keywords: Feature Extraction, Histogram Oriented Gradient (HOG), Convolution Neural Network (CNN), Machine Learning

[This article belongs to International Journal of Wireless Security and Networks (ijwsn)]

How to cite this article:
Pradeep N.R, Manohara T N, Sreenivasa T V. A Novel Approach to Fingerprint Authentication Using Histogram Oriented Gradients for Feature Extraction and Machine Learning Convolution Neural Network for Classification. International Journal of Wireless Security and Networks. 2023; 01(02):1-12.
How to cite this URL:
Pradeep N.R, Manohara T N, Sreenivasa T V. A Novel Approach to Fingerprint Authentication Using Histogram Oriented Gradients for Feature Extraction and Machine Learning Convolution Neural Network for Classification. International Journal of Wireless Security and Networks. 2023; 01(02):1-12. Available from: https://journals.stmjournals.com/ijwsn/article=2023/view=118749

References

1. Vijayakumar T. Synthesis of Palm Print in Feature Fusion Techniques for Multimodal Biometric Recognition System Online Signature. Journal of Innovative Image Processing (JIIP). 2021; 3(02): 131–143.

2. Oloyede M, Hancke G. Unimodal and Multimodal Biometric Sensing Systems: A Review. IEEE Access. 2016; 4: 7532–7555.

3. Rahmawati E, Mariska Listyasari, Adam Shidqul Aziz. Digital signature on file using biometric fingerprint with fingerprint sensor on smartphone in Engineering Technology and Applications. International Electronics Symposium. 2017; 234–238.

4. Molaei S, Shiri Ahmad Abadi ME. Maintaining filter structure: A Gabor-based convolutional neural network for image analysis. Appl Soft Comput. 2020; 88: 105960. https://doi.org/10.1016/j.asoc. 2019.105960.

5. Phillips PJ, Martin A, Wilson CL, Przybocki M. An introduction evaluating biometric systems. Computer. 2000 Feb;33(2):56–63.

6. Benaliouche H, Touahria M. Comparative study of multimodal biometric recognition by fusion of iris and fingerprint. Scientific World Journal. 2014; 2014: 829369.

7. Jain AK, Ross A, Prabhakar S. An introduction to biometric recognition. IEEE Trans Circuits Syst Video Technol. 2004; 14(1): 4–20.

8. Kataria AN, Adhyaru Dipak M, Sharma Ankit K, Zaveri Tanish H. A survey of automated biometric authentication techniques in Engineering. Nirma University International Conference IEEE. 2013; 1–6.

9. Jain Anil K, Karthik Nandakumar, Arun Ross. 50 years of biometric research: Accomplishments, challenges, and opportunities. Pattern Recognit Lett. 2016; 79: 80–105.

10. Bartunek Josef Strom, Mikael Nilsson, Benny Sallberg, Ingvar Claesson. Adaptive fingerprint image enhancement with emphasis on preprocessing of data. IEEE Trans Image Process. 2013; 22(2): 644–656.

11. Pradeep NR, Ravi J. Machine Learning based Artificial Neural Networks for Fingerprint Recognition. International Journal of Image and Video Processing (IJIVP). 2022 Nov; 13(02): 2874–2882. DOI: 10.21917/IJIVP.2022.0410.

12. Pradeep NR, Ravi J. An Accurate Fingerprint Recognition Algorithm Based on Histogram Oriented Gradient (HOG) Feature Extractor. International Journal of Electrical Engineering and Technology (IJEET). 2021 Feb; 12(02): 19–32. DOI: 10.34218/IJEET.12.2.2021.003.

13. Vinod Kumar, Srikantaswamy R. A Comparative Analysis of Histogram of Gradient (HOG), Gabor Filter Bank and DCT based Feature Extraction Methods used for Fingerprint Recognition. Int J Sci Eng Res. 2016 Apr; 7(4): 321–326.

14. Chaudhari Jitendra P, Mewada Hiren K, Patel Amit V, Mahant Keyur K, Vala Alpesh D. Supervised Feature Reduction Technique for Biometric Recognition using Palm Print Modalities. Biosci Biotechnol Res Commun. 2020 Jan–Mar; 13(1): 195–200.

15. Sree Lakshmi KJ, Therese Yamuna Mahesh. Human Identification Based on the Histogram of Oriented Gradients. Int J Eng Res Technol. 2014 Jul; 3(7): 1611–1614.

16. Ahmad Mostafa A, Ismail Ahmed H, Nadir Omer. An Accurate Multi-Biometric Personal Identification Model using Histogram of Oriented Gradients. Int J Adv Comput Sci Appl. 2018; 9(5): 313–319.

17. Himabindu Sathyaveti, Amarendra Jadda. Fingerprint Liveness Detection from Single Image using SURF & PHOG. Int J Innov Res Sci Eng Technol. 2017 May; 6(5): 7693–7703.

18. Daesung Moon, Sungju Lee, Yongwha Chung. Implementation of Automatic Fuzzy Fingerprint Vault. Proceedings of International conference on Machine Learning and Cybernetics. 2008 Jul; 3781–3786.

19. Jain A, Hong L, Bolle R. On-line Fingerprint Verification. IEEE Trans Pattern Anal Mach Intell. 1997 Apr; 19(4): 302–314.

20. Greenberg S, Aladjem M, Kogan D. Fingerprint Image Enhancement using Filtering Techniques. National Conference on Real-Time Imaging. 2002; 227–236.

21. Seifedine Kadry, Aziz Barbar. Design of Secure Mobile Communication using Fingerprint. Eur J Sci Res. 2009; 30(1): 138–145.

22. Tabassam Nawaz, Saim Pervaiz, Arash Korrani. Development of Academic Attendance Monitoring System using Fingerprint Identification. Int J Comput Sci Netw Secur. 2009 May; 9(5): 164–168.

23. Kass M, Witkin A. Analysing Oriented Patterns. Proceedings of Journal of Computer Vision Graphics Image Process. 1987; 37: 362–385.

24. Bazen, Gerez. Extraction of Singular points from Directional Fields of Fingerprints. Annual Centre for Telematics and Information Technology Workshop. 2002 Jul; 24: 905–919.

25. Hong L, Jain AK, Pankanti S, Bolle R. Fingerprint Enhancement. Proceedings of 3rd IEEE Workshop on Applications of Computer Vision. 1996; 202–207.

26. Radzi SA, Hani MK, Bakhteri R. Finger-vein biometric Identification using convolutional neural network. Turk J Electr Eng Comput Sci. 2016; 24(3): 1863–1878.

27. Xie C, Kumar A. Finger vein identification using convolutional neural network and supervised discrete hashing. Pattern Recognit Lett. 2019 Mar; 119: 148–156.

28. Qin H, El-Yacoubi MA. Deep representation- based feature extraction and recovering for finger-vein verification. IEEE Trans Inf Forensics Secur. 2017 Aug; 12(8): 1816–1829.

29. Bharadi VA, Pandya B, Nemade B. Multimodal biometric recognition using iris & fingerprint: By texture feature extraction using Hybrid Wavelets. 5th International Conference-Confluence: The Next Generation Information Technology Summit (Confluence), Noida. 2014; 697–702. doi: 10.1109/CONFLUENCE. 2014.6949309.

30. Ali MMH, Mahale VH, Yannawar P, Gaikwad AT. Fingerprint Recognition for Person Identification and Verification based on Minutiae Matching. Proceedings of IEEE 6th International Advanced Computing Conference. 2016; 332–339.

31. Satishkumar Chavan, Parth Mundada, Devendra Pal. Fingerprint Authentication using Gabor filter based Matching Algorithm. Proceedings of IEEE International Conference on Technologies for Sustainable Development. 2015; 1–6.

32. Yang J, Wu Z, Zhang J. A Robust Fingerprint Identification Method by Deep Learning with Gabor Filter Multidimensional Feature Expansion. 4th International Conference, ICCCS 2018, Haikou, China. 2018 Jun 8–10; 447–57.

33. Michelsanti D, Ene AD, Guichi Y, Stef R, Nasrollahi K, Moeslund TB. Fast Fingerprint Classification with Deep Neural Networks. 12th International Conference on Computer Vision Theory and Applications. (VISAPP 2017) DOI: 10.5220/0006116502020209.

34. Pushpalatha KN, Arvind Kumar Gautham. Fingerprint Verification in Personal Identification by Applying Local Walsh Hadamard Transforms and Gabor Coefficients. International Journal on Image and Video Processing (IJIVP). 2017 May; 7(4): 1525–1532.

35. Nguyen HT, Long The Nguyen. Fingerprints Classification through Image Analysis and Machine Learning Method. Algorithms. 2019 Nov; 12(11): 241.

36. Bhavesh Pandya, Georgina Cosma, Alani Ali A, Aboozar Taherkhani, Vinayak Bharadi, McGinnity TM. Fingerprint Classification using a Deep Convolutional Neural Network. 4th IEEE International Conference on Information Management. 2018; 86–91.


Regular Issue Subscription Review Article
Volume 01
Issue 02
Received 20/07/2023
Accepted 29/07/2023
Published 22/09/2023