Hand Gesture Based Biometric Authentication Using Machine Learning Approaches

Yıl 2025, Cilt: 12 Sayı: 1, 274 - 289, 30.05.2025

Zekeriya Katılmış

https://doi.org/10.35193/bseufbd.1555404

Cited By: 1

Öz

Authentication is becoming an important task in the field of modern technology. It is a process that allows a device to confirm that it recognizes a user interacting with a system entity. In this study, a single-handed gesture-based user authentication using the Leap Motion (LM) device has been investigated. The study consists of hand gesture tracking, acquisition of image frames, preprocessing, feature extraction and selection, dimension reduction, classification, and validation steps. A dataset was collected by 40 users by determining 85 features prepared by considering the similarities and differences of hand biometrics. Comparison analyses were performed by applying the Pearson Correlation Coefficient (PCC) feature selection algorithm and Linear Discriminant Analysis (LDA) and Principal Component Analysis (PCA) dimensionality reduction methods to this dataset. The verification performance was tested with different machine learning algorithm methods. A 5-fold cross-validation method was used to test the validity of this proposed system and the accuracy of the obtained results. In biometric authentication, the best result was obtained with the kernel-based extreme learning machine (K-ELM) approach with a rate of 96.50%. When the applications were examined in all stages, it was observed that the K-ELM classifier maintained its performance rates and gave the highest performance rate. At the same time, it was seen that the K-ELM classifier has a stable structure.

Anahtar Kelimeler

Biometrics , authentication , hand gesture , machine learning , feature extraction

Makine Öğrenimi Yaklaşımları Kullanarak El Hareketi Tabanlı Biyometrik Kimlik Doğrulama

Öz

Kimlik doğrulama, modern teknoloji alanında önemli bir görev haline gelmektedir. Bu, bir cihazın bir sistem varlığıyla etkileşimde bulunan bir kullanıcıyı tanıdığını onaylamasına olanak tanıyan bir süreçtir. Bu çalışmada, Leap Motion (LM) cihazı kullanılarak tek elle gerçekleştirilen hareket bazlı kullanıcı kimlik doğrulama üzerine çalışılmıştır. Çalışma el hareketi takip, görüntü karelerinin elde edilmesi, önişlem, öznitelik çıkarımı ve seçimi, boyut indirgeme, sınıflandırma ve doğrulama adımlarından oluşmaktadır. El biyometrisinin benzerlik ve farklılıkları dikkate alınarak hazırlanan 85 özellik belirlenerek 40 kullanıcı tarafından veri kümesi oluşturulmuştur. Bu veri kümesine Pearson Korelasyon Katsayısı (PCC) özellik seçim algoritması ile Doğrusal Ayırım Analizi (LDA) ve Temel Bileşenler Analizi (PCA) boyut indirgeme yöntemleri uygulanarak karşılaştırma analizleri yapılmıştır. Doğrulama başarımı farklı makine öğrenimi algoritma yöntemleri ile test edilmiştir. Önerilen bu sistemin geçerliliği ve elde edilen sonuçların doğruluğunu test etmek için 5 katlamalı çapraz doğrulama yöntemi kullanılmıştır. Biyometrik kimlik doğrulama, en iyi sonuç %96,50 oranı ile çekirdek tabanlı aşırı öğrenme makinesi (K-ELM) yaklaşımı ile elde edilmiştir. Tüm aşamalarda uygulamalara bakıldığında, K-ELM sınıflandırıcının başarım oranlarını koruduğunu ve en yüksek başarım oranını verdiği gözlemlenmiştir. Aynı zamanda K-ELM sınıflandırıcının kararlı bir yapıda olduğu görülmüştür.

Anahtar Kelimeler

Biyometrik , kimlik doğrulama , el hareketi , makine öğrenimi , özellik çıkarımı

Kaynakça

• Selbes, B., & Elihoş, A. (2023). Deep Learning Based Latent Palmprint Recognition. In 2023 31st Signal Processing and Communications Applications Conference (SIU) (pp. 1-4). IEEE.
• Iula, A. (2021). Biometric recognition through 3D ultrasound hand geometry. Ultrasonics, 111, 106326.
• Aydemir, E., Tuncer, T., Dogan, S., & Unsal, M. (2021). A novel biometric recognition method based on multi kernelled bijection octal pattern using gait sound. Applied Acoustics, 173, 107701.
• Devi, R. M., Keerthika, P., Suresh, P., Sarangi, P. P., Sangeetha, M., Sagana, C., & Devendran, K. (2022). Retina biometrics for personal authentication. In Machine Learning for Biometrics (pp. 87-104).
• Ammour, B., Boubchir, L., Bouden, T., & Ramdani, M. (2020). Face–iris multimodal biometric identification system. Electronics, 9(1), 85.
• Bibi, K., Naz, S., & Rehman, A. (2020). Biometric signature authentication using machine learning techniques: Current trends, challenges and opportunities. Multimedia Tools and Applications, 79(1), 289-340.
• Wong, A. M. H., & Kang, D. K. (2016). Stationary hand gesture authentication using edit distance on finger pointing direction interval. Scientific Programming, 2016(1). DOI: 10.1155/2016/7427980.
• Imura, S., & Hosobe, H. (2018). A hand gesture-based method for biometric authentication. In Human-Computer Interaction. Theories, Methods, and Human Issues: 20th International Conference, HCI International 2018, Las Vegas, NV, USA, July 15–20, 2018, Proceedings, Part I 20 (pp. 554-566). Springer International Publishing.
• Maruyama, K., Shin, J., Kim, C. M., & Chen, C. L. (2017). User authentication using leap motion. In Proceedings of the international conference on research in adaptive and convergent systems (pp. 213-216).
• Bernardos, A. M., Sánchez, J. M., Portillo, J. I., Wang, X., Besada, J. A., & Casar, J. R. (2016). Design and deployment of a contactless hand-shape identification system for smart spaces. Journal of Ambient Intelligence and Humanized Computing, 7, 357-370.
• Manabe, T., & Yamana, H. (2019). Two-factor authentication using leap motion and numeric keypad. In HCI for Cybersecurity, Privacy and Trust: First International Conference, HCI-CPT 2019, Held as Part of the 21st HCI International Conference, HCII 2019, Orlando, FL, USA, July 26–31, 2019, Proceedings 21 (pp. 38-51). Springer International Publishing.
• Xu, W., Tian, J., Cao, Y., & Wang, S. (2017). Challenge-response authentication using in-air handwriting style verification. IEEE Transactions on Dependable and Secure Computing, 17(1), 51-64. doi:10.1109/TDSC.2017.2752164.
• Lu, D., Xu, K., & Huang, D. (2017). A data driven in-air-handwriting biometric authentication system. In 2017 IEEE International Joint Conference on Biometrics (IJCB) (pp. 531-537). IEEE.
• Lu, D., Huang, D., & Rai, A. (2019). FMHash: Deep hashing of In-Air-Handwriting for user identification. In ICC 2019-2019 IEEE International Conference on Communications (ICC) (pp. 1-7). IEEE.
• Saritha, L. R., Thomas, D., Mohandas, N., & Ramnath, P. (2017). Behavioral biometric authentication using Leap Motion sensor. Int. J. Latest Trends Eng. Technol, 8(1), 643-649.
• Xiao, G., Milanova, M., & Xie, M. (2016). Secure behavioral biometric authentication with leap motion. In 2016 4th international symposium on digital forensic and security (isdfs) (pp. 112-118). IEEE.
• Taher, M. M., & George, L. E. (2022). A digital signature system based on hand geometry. Journal of Algebraic Statistics, 13(3), 4538-4556.
• Chahar, A., Yadav, S., Nigam, I., Singh, R., & Vatsa, M. (2015). A leap password based verification system. In 2015 IEEE 7th International Conference on Biometrics Theory, Applications and Systems (BTAS) (pp. 1-6). IEEE.
• Shin, J., Islam, M. R., Rahim, M. A., & Mun, H. J. (2020). Arm movement activity based user authentication in P2P systems. Peer-to-peer networking and applications, 13(2), 635-646. DOI: 10.1007/s12083-019-00775-7.
• Wu, J., Konrad, J., & Ishwar, P. (2013). Dynamic time warping for gesture-based user identification and authentication with Kinect. In 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (pp. 2371-2375). IEEE.
• Lai, K., Konrad, J., & Ishwar, P. (2012). Towards gesture-based user authentication. In 2012 IEEE Ninth International Conference on Advanced Video and Signal-Based Surveillance (pp. 282-287). IEEE.
• LM Cihazı. (2023). Leap Motion C# SDK Documentation. Retrieved from https://developer-archive.leapmotion.com/documentation/csharp/index.html. Accessed September 11, 2024.
• Katılmış, Z., & Karakuzu, C. (2023). Double handed dynamic Turkish Sign Language recognition using Leap Motion with meta learning approach. Expert Systems with Applications, 228, 120453.
• Katılmış, Z., & Karakuzu, C. (2021). ELM based two-handed dynamic Turkish sign language (TSL) word recognition. Expert Systems with Applications, 182, 115213.
• Ameur, S., Khalifa, A. B., & Bouhlel, M. S. (2020). Hand-gesture-based touchless exploration of medical images with leap motion controller. In 2020 17th International multi-conference on systems, signals & devices (SSD) (pp. 6-11). IEEE.
• Ferreira, S. C., Chaves, R. O., Seruffo, M. C. D. R., Pereira, A., Azar, A. P. D. S., Dias, Â. V., ... & Brito, M. V. H. (2020). Empirical evaluation of a 3D virtual simulator of hysteroscopy using Leap Motion for gestural interfacing. Journal of Medical Systems, 44, 1-10.
• Korayem, M. H., Madihi, M. A., & Vahidifar, V. (2021). Controlling surgical robot arm using leap motion controller with Kalman filter. Measurement, 178, 109372.
• Korayem, M. H., Vosoughi, R., & Vahidifar, V. (2022). Design, manufacture, and control of a laparoscopic robot via Leap Motion sensors. Measurement, 205, 112186.
• Najafinejad, A., & Korayem, M. H. (2023). Detection and minimizing the error caused by hand tremors using a leap motion sensor in operating a surgeon robot. Measurement, 221, 113544.
• Tarakci, E., Arman, N., Tarakci, D., & Kasapcopur, O. (2020). Leap Motion Controller–based training for upper extremity rehabilitation in children and adolescents with physical disabilities: A randomized controlled trial. Journal of Hand Therapy, 33(2), 220-228.
• Aguilar-Lazcano, C. A., & Rechy-Ramirez, E. J. (2020). Performance analysis of Leap motion controller for finger rehabilitation using serious games in two lighting environments. Measurement, 157, 107677.
• Dunai, L., Novak, M., & García Espert, C. (2020). Human hand anatomy-based prosthetic hand. Sensors, 21(1), 137.
• Geng, J., Zhang, W., Ge, Y., Wang, L., Huang, P., Liu, Y., ... & Cheng, X. (2024). Inter-rater variability and repeatability in the assessment of the Tanner–Whitehouse classification of hand radiographs for the estimation of bone age. Skeletal Radiology, 1-8.
• Vishnoi, V. K., Kumar, K., & Kumar, B. (2022). A comprehensive study of feature extraction techniques for plant leaf disease detection. Multimedia Tools and Applications, 81(1), 367-419.
• Uçar, M. K., Örenç, S., Bozkurt, M. R., & Bilgin, C. (2017). Evaluation of the relationship between chronic obstructive pulmonary disease and photoplethysmography signal. In 2017 Medical Technologies National Congress (TIPTEKNO) (pp. 1-4). IEEE.
• Şeker, D., & Özerdem, M. S. (2020). Classification and Statistical Analysis of Schizophrenic and Normal EEG Time Series. In 2020 Medical Technologies Congress (TIPTEKNO) (pp. 1-4). IEEE.
• Sun, S., Hu, M., Wang, S., & Zhang, C. (2023). How to capture tourists’ search behavior in tourism forecasts? A two-stage feature selection approach. Expert Systems with Applications, 213, Article 118895. https://doi.org/10.1016/j.eswa.2022.118895
• Daru, A. F., Hanif, M. B., & Widodo, E. (2021). Improving neural network performance with feature selection using Pearson correlation method for diabetes disease detection. JUITA: JurnalInformatika, 9(1), 123–130. https://doi.org/10.30595/juita. v9i1.9941
• Hasan, B. M. S., & Abdulazeez, A. M. (2021). A review of principal component analysis algorithm for dimensionality reduction. Journal of Soft Computing and Data Mining, 2(1), 20-30
• Choubey, D. K., Kumar, M., Shukla, V., Tripathi, S., & Dhandhania, V. K. (2020). Comparative analysis of classification methods with PCA and LDA for diabetes. Current diabetes reviews, 16(8), 833-850.
• Martinez, M., & Kak, A. C. (2001). PCA versus LDA. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23, 228–233. https://doi.org/10.1109/34.908974
• Cruz, J. A., & Wishart, D. S. (2006). Applications of machine learning in cancer prediction and prognosis. Cancer informatics, 2, 117693510600200030.
• Guang-BinHuang, Zhu, Q.-Y., & Siew, C.-K. (2006). Extreme learning machine: Theory and applications. Neurocomputing , 70, s. 489–501.
• Tang, J., Deng, C., Huang, G.-B., & Zhao, B. (2015). Compressed-Domain Ship Detection on Spaceborne Optical Image Using Deep Neural Network and Extreme Learning Machine. IEEE Transactions on Geoscience and Remote Sensing , 53 (3), s. 1174-1185.
• Huang, G. B. (2014). An Insight into Extreme Learning Machines: Random Neurons, Random Features and Kernels. Cognitive Computation , 6 (3), s. 376-390.
• Cao, J., Lin, Z., Huang, G. B., & Liub, N. (2012). Voting based extreme learning machine. Information Sciences , 185 (1), s. 66–77.
• Cambria, E., Huang, G.-B., Kasun, L. L., Zhou, H., Vong, C. M., Lin, J., et al. (2013). Extreme learning machines. IEEE Intelligent Systems , 28 (6), s. 30–59.
• Cambria, E., Huang, G. B., Kasun, L. L. C., Zhou, H., Vong, C. M., Lin, J., ... & Liu, J. (2013). Extreme learning machines [trends & controversies]. IEEE intelligent systems, 28(6), 30-59.
• Cao, F., Yang, Z., Ren, J., Chen, W., Han, G., & Shen, Y. (2019). Local block multilayer sparse extreme learning machine for effective feature extraction and classification of hyperspectral images. IEEE Transactions on Geoscience and Remote Sensing, 57(8), 5580-5594.
• Cambria, E., Huang, G. B., Kasun, L. L. C., Zhou, H., Vong, C. M., Lin, J., ... & Liu, J. (2013). Extreme learning machines [trends & controversies]. IEEE intelligent systems, 28(6), 30-59.
• Pal, M., Maxwell, A. E., & Warner, T. A. (2013). Kernel-based extreme learning machine for remote-sensing image classification. Remote Sensing Letters, 4(9), 853-862.
• Chen, C., Li, W., Su, H., & Liu, K. (2014). Spectral-spatial classification of hyperspectral image based on kernel extreme learning machine. Remote Sensing, 6(6), 5795-5814.
• Huang, G. B., Zhou, H., Ding, X., & Zhang, R. (2012). Extreme learning machine for regression and multiclass classification. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 42(2), 513-529.
• Zhou, L., & Ma, L. (2019). Extreme learning machine-based heterogeneous domain adaptation for classification of hyperspectral images. IEEE Geoscience and Remote Sensing Letters, 16(11), 1781-1785.
• Huang, C.-L., Chen, M.-C., & Wang, C.-J. (2007). Credit scoring with a data mining approach based on support vector machines. Expert Systems with Applications, 33, s. 847–856.
• Tiboni, M., & Remino, C. (2024). Condition Monitoring of Pneumatic Drive Systems Based on the AI Method Feed-Forward Backpropagation Neural Network. Sensors, 24(6), 1783. https://doi.org/10.3390/s24061783
• Büyük, O., & Arslan, L. M. (2018). Age identification from voice using feed-forward deep neural networks. In 2018 26th Signal Processing and Communications Applications Conference (SIU) (pp. 1-4). IEEE.
• Baştürk, A., Yüksel, M. E., Çalışkan, A., & Badem, H. (2017). Deep neural network classifier for hand movement prediction. In 2017 25th Signal Processing and Communications Applications Conference (SIU) (pp. 1-4). IEEE.
• Hinton, G. E., & Salakhutdinov, R. R. (2006). Reducing the dimensionality of data with neural networks. Science, 313(5786), 504-507. https://doi.org/10.1126/science.112764.