CFP last date
15 July 2024
Reseach Article

Analysis of ANN Training Algorithms for Hand Geometry-based Access Control

by Kazeem B. Adedeji, Apena Waliu O., Adu Michael R.
International Journal of Applied Information Systems
Foundation of Computer Science (FCS), NY, USA
Volume 12 - Number 43
Year of Publication: 2024
Authors: Kazeem B. Adedeji, Apena Waliu O., Adu Michael R.

Kazeem B. Adedeji, Apena Waliu O., Adu Michael R. . Analysis of ANN Training Algorithms for Hand Geometry-based Access Control. International Journal of Applied Information Systems. 12, 43 ( Mar 2024), 12-22. DOI=10.5120/ijais2024451965

@article{ 10.5120/ijais2024451965,
author = { Kazeem B. Adedeji, Apena Waliu O., Adu Michael R. },
title = { Analysis of ANN Training Algorithms for Hand Geometry-based Access Control },
journal = { International Journal of Applied Information Systems },
issue_date = { Mar 2024 },
volume = { 12 },
number = { 43 },
month = { Mar },
year = { 2024 },
issn = { 2249-0868 },
pages = { 12-22 },
numpages = {9},
url = { },
doi = { 10.5120/ijais2024451965 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
%0 Journal Article
%1 2024-03-20T22:11:44+05:30
%A Kazeem B. Adedeji
%A Apena Waliu O.
%A Adu Michael R.
%T Analysis of ANN Training Algorithms for Hand Geometry-based Access Control
%J International Journal of Applied Information Systems
%@ 2249-0868
%V 12
%N 43
%P 12-22
%D 2024
%I Foundation of Computer Science (FCS), NY, USA

Hand geometry-based identification systems are one of the most widely used access control systems due to their simplicity and low cost. Extracted features of hand images are deployed to train a machine learning algorithm. The required hand features include palm size as well as finger length and width. During verification, unauthorized hand images are rejected if their features do not match those already stored in the database. Several machine learning algorithms have been employed for access control, but artificial neural network (ANN) techniques are a major contender due to their robustness and accuracy to parameter changes. The performance of the hand geometry technique is dependent on the training model used to assess the efficacy of the ANN. The study examined four ANN training algorithms: the Levenberg-Marquardt algorithm (LMA), BFGS Quasi-Newton (GFGS-QN), resilient back propagation (RBP), and scaled conjugate gradient (SCG) algorithms. The results revealed through numerical investigation showed that the LMA outperformed the rest of the studied ANN algorithms using mean square error, image gradient coefficient, histogram of errors, regression, accuracy, and precision. LMA ranked first with positive outcomes of the lowest mean square error of 8.8383×10-5, 99.999% regression value, and 99.99% accuracy, respectively. The study complements the performance of LMA with the ANN training algorithm at 13 epochs to reach its best performance and its convergence strength. LMA proves to be the most suitable ANN training algorithm for hand geometry recognition applications.

  1. Dutagaci, H., Sankur, S., and Yörük, E. 2008. A comparative analysis of global hand appearance-based person recognition. Journal of Electronic Imaging, 17(1), 011018.
  2. Pereira, T.M., Coneicao, R.C., Sencadas, V., and Sebastiao, R. 2023. Biometric recognition: A systematic review on electrocardiogram data acquisition methods. Sensors, 23(3), 1-31.
  3. Adedeji, K.B., and Esan, O.A. 2022. A GUI-based peg-free hand geometry recognition for biometric access control using artificial neural network. Journal of Engineering Advancements, 3(04), 131-143.
  4. Angadi, S., and Hatture, S. 2018. Hand geometry based user identification using minimal edge connected hand image graph. IET Computer Vision, 12, 744-752.
  5. Dhole, S.A., and Patil, V.H. 2012. Person identification using peg free hand geometry measurement. International Journal of Engineering Science and Technology, 4, 2942-2949.
  6. Sahoo, J.P., Sahoo, S.P., Ari, S., and Patra, S.K. 2023. DeReFNet: Dual-stream dense residual fusion network for static hand gesture recognition. Displays, 77, 102388.
  7. Miah, A.S.M., Hasan, M.A.M., and Shin, J. 2023. Dynamic hand gesture recognition using multi-branch attention based graph and general deep learning model. IEEE Access, 11, 4703-4716.
  8. Byberi, A., Ravan, M., and Amineh, R.K.. 2023. GloveSense: A hand gesture recognition system based on inductive sensing. IEEE Sensor Journal, 23(9), 9210-9219.
  9. Abiodun, O.I., Jantan, A., A.E. Omolara, K.V., Dada, N., Mohamed, N., and Arshad, H. 2018. State-of-the-art in artificial neural network applications: A survey. Heliyon, 4, e00938.
  10. Erkaymaz, O. 2020. Resilient back-propagation approach in small-word feed-forward neural network topology based on Newman-Watts algorithm. Neural Computing and Applications, 30, 16279-16289.
  11. He, C., Ma, M., and Wang, P. 2020. Extract interpretability-accuracy balanced rules from artificial neural networks: A review, Neurocomputing, 387, 346-358.
  12. Robles-Velasco, A., Munuzuri, J., Onieva, L., and Rodriquez-Palero, M. 2021. Trends and application of machine learning in water supply network management. Journal of Industrial Engineering and Management, 14, 45-54.
  13. Igel, C., and Husken, M. 2003. Empirical evaluation of the improved Rprop learning algorithms. Neurocomputing, 50, 105-123.
  14. Nanni, L., Lumini, A., Ferrara, M., and Capelli, R. 2015. Combining biometric matches by means of machine learning and statistical approaches. Neurocomputing, 149, 526-535.
  15. Wu, J.D., and Liu, C.T. 2011. Finger-vein pattern identification using principal component analysis and the neural network technique. Expert Systems with Applications, 38, 5423-5427.
  16. Raji, R.K., Adjeisah, M., Miao, X., and Wan, A. 2020. A novel respiration pattern biometric prediction system based on artificial neural network. Sensor Review, 40, 8-16.
  17. Siswanto, A., Tarigan, P., and Fahmi, F. 2013. Design of contactless hand biometric system with relative geometric parameters. In: Proceedings of the IEEE 3rd International Conference on Instrumentation, Communications, Information Technology and Biomedical Engineering, 7-8 November, Bandung, Indonesia, pp. 199-203.
  18. Salve, S.S., and Narote, S.P. 2016. Iris recognition using SVM and ANN. In: Proceedings of the IEEE International Conference on Wireless Communications, Signal Processing and Networking, 23-25 March, Chennai, India, pp. 474-478.
  19. Patro, K.K., and Kumar, P.R. 2017. Machine learning classification approaches for biometric recognition system using ECG signals. Journal of Engineering Science and Technology Review, 10, 1-8.
  20. Kim, S., Yeun, C.Y., and Yoo, P.D. 2019. Enhanced machine learning based biometric authentication system using RR-interval framed electrocardiograph. IEEE Access, 7, 168669- 168674.
  21. Patro, K.K., Prakash, J.A., Rao, J.M., and Kumar, R.P. 2022. An efficient optimized feature selection with machine learning approach for ECG biometric recognition. IETE Journal of Research, 68(4), 2743-2754.
  22. Abozaid, A., Haggag, A., Kasban, H., and Eltokhy, M. 2019. Multimodal biometric scheme for human authentication technique based on voice and face recognition fusion. Multimedia Tools and Applications, 78, 16345-16361.
  23. Thamaraimanalan, T., Pranavakumar, S., Lingeswaran, R.A, Kabileshar, R.M., and Sarankarthick, M. 2021. Multi biometric authentication using SVM and ANN classifiers. Irish Interdisciplinary Journal of Science & Research, 5, 118-130.
  24. Patterh, M.S. 2017. A biometric fusion based on face and fingerprint recognition using ANN. International Journal on Recent and Innovation Trends in Computing and Communication, 5, 88-92.
  25. Ali, H., and Salami, M.J. 2009. Keystroke pressure based typing biometrics authentication system by combining ANN and ANFIS-based classifiers. In: Proceedings of the IEEE 5th International Colloquium on Signal Processing & Its Applications, 6-8 March, Kuala Lumpur, Malaysia, pp. 198-203.
  26. Harun, N., Woo, W.L., and Dlay, S.S. 2010. Performance of keystroke biometrics authentication system using artificial neural network (ANN) and distance classifier method. In: Proceedings of the IEEE International Conference on Computer and Communication Engineering, 11-12 May, Kuala Lumpur, Malaysia, pp. 1-6.
  27. Harun, N., Dlay, S.S., and Woo, W.L. 2010. Performance of keystroke biometrics authentication system using Multilayer Perceptron neural network (MLP NN). In: Proceedings of the IEEE 7th International Symposium on Communication Systems, Networks & Digital Signal Processing, 21-23 July, pp. 711-714.
  28. Ranganathan, A. 2004. The Levenberg-Marquardt algorithm. Tutorial on LM Algorithm, 11, 101-110.
  29. Lourakis, M.I. 2005. A brief description of the Levenberg-Marquardt algorithm implemented by levmar. Foundation of Research and Technology, 4, 1-6.
  30. Amini, K., and Rostami, F. 2016. Three-steps modified Levenberg–Marquardt method with a new line search for systems of nonlinear equations. Journal of Computational and Applied Mathematics, 300, 30-42
  31. De Rubio, J.J. 2020. Stability analysis of the modified Levenberg-Marquardt algorithm for the artificial neural network training. IEEE Transactions on Neural Networks and Learning Systems, 32(8), 3510-3524.
  32. Babani, L., Jadhav, S., and Chaudhari, B. 2016. Scaled conjugate gradient based adaptive ANN control for SVM-DTC induction motor drive. In: Proceedings of the 12th IFIP International Conference on Artificial Intelligence Applications and Innovations, Sepetember, Thessaloniki, Greece. pp.384-395.
  33. Prasad, N., Singh, R., and Lal, S.P. 2013. Comparison of back propagation and resilient propagation algorithm for spam classification. In: Proceedings of the IEEE 5th International Conference on Computational Intelligence, Modelling and Simulation, pp. 29-34.
  34. Andrei, N. 2007. Scaled conjugate gradient algorithms for unconstraint optimization. Computational Optimization and Applications, 38, 416-416.
  35. Wang, S., and Guan, H. 2013. A scaled conjugate gradient method for solving monotone nonlinear equations with convex constraints. Journal of Applied Mathematics, 2013, 1-7.
  36. Dai, Y.H. 2002. Convergence properties of the BFGS algorithm. SIAM Journal of Optimization, 13, 693-701.
  37. Yang, T., Li, P., and Wang, X. 2020. Convergence analysis of an improved BFGS method and its application in the Muskingum model. Mathematical Problems in Engineering, 2020, 1-9.
  38. Mishra, S.K., Panda, G., Chakraborty, S.K., Samei, M.E., and Ram, B. 2020. On q-BFGS algorithm for unconstrained optimization problems. Advances in Difference Equations, 2020(1), 1-24.
  39. Li, D., and Fukushima, M. 2001. A modified BFGS method and its global convergence in noncovex minimization. Journal of Computational and Applied Mathematics, 29, 15-35.
  40. Lai, K.K., Mishra, S.K., Panda, G., Chakraborty, S.K., Samei, M.E., and Ram, B. 2020. A limited memory q-BFGS algorithm for unconstraint optimization problems. Journal of Applied Mathematics and Computing, 66, 183-202.
  41. Fariq, H., and Simoncelli, E.P. 2004. Differentiation of discrete multi-dimensional signals. IEEE Transactions on Image Processing, 13, 496-508.
  42. Hast, A., Simple filter design for first and second order derivatives by a double filtering approach. Pattern Recognition Letters, vol. 42, 2014, pp. 65-71.
  43. Khosravi, M.R., & Yazdi, M., (2018). A lossless data hiding scheme for medical images using a hybrid solution based on IBEW error histogram computation and quartered interpolation with greedy weights. Neural Computing and Applications, 30, 2017-2028.
Index Terms

Computer Science
Information Sciences


Access control ANN hand geometry LMA BFGS Quasi-newton RBP SCG