A Novel Fuzzy Logic Based Hand Gesture Recognition System

Öz

In this proposed study, a Fuzzy Logic System (FLS) was developed to classify and detect hand movements. The designed FLS system consists of a Fuzzifier, Inference Engine, Knowledge Base, and Defuzzifier. The Mamdani technique was used as the Inference Engine, and the centroid method was used for Defuzzification. Five input variables (Flex1-5) and one output variable (Sign) were used to create a rule base with 94 rules. A sensor array was placed on a glove to generate data, and a data collection circuit was established. Movements were performed through this circuit to create the rule bases. A total of 15.030 data points were analyzed to develop the FLS. According to the results, the movements (97.5%) were detected successfully.

Anahtar Kelimeler

• Flex sensor
• fuzzy logic
• hand gesture recognition

Kaynakça

1. [1] Y. Zhang et al., “Mechanomyography signals pattern recognition in hand movements using swarm intelligence algorithm optimized support vector machine based on acceleration sensors”, Medical Engineering and Physics 124 (2024) 104060.
2. [2] M.A. Rahaman, M.H. Ali, and M. Hasanuzzaman, “Real-time computer vision-based gestures recognition system for Bangla sign language using multiple linguistic features analysis”, Multimedia Tools and Applications, 83, 22261–22294 (2024). https://doi.org/10.1007/s11042-023-15583-8.
3. [3] World Health Organization, “Deafness and hearing loss”, https://www.who.int/es/news-room/fact-sheets/detail/deafness-and-hearing-loss, 2021, Online; Accessed July 19.
4. [4] H. Yakut, “İşaret dili harflerinin görüntü işleme yöntemleriyle tanınması için bir uygulama”, Yüksek Lisans Tezi, Fırat Üniversitesi, Ocak 2013.
5. [5] F. ShengChen, C. MingFu, and C. LinHuang, “Hand gesture recognition using a real-time tracking method and hidden Markov models”, Image and Vision Computing, 21(8), 1 August 2003, Pages 745-758.
6. [6] D. Wu, L. Pigou, P.J. Kindermans, N.D.H. Le, L. Shao, J. Dambre, and J.M. Odobez, “Deep dynamic neural networks for multimodal gesture segmentation and recognition”, IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(8), 1583-1597, 2016.
7. [7] O. Güler, & I. Yücedağ, “Derin öğrenme ile el hareketi tanıma üzerine yapılan çalışmaların incelenmesi”, 21. Akademik Bilişim Konferansı, 2019, Ordu/Turkey.
8. [8] G. Devineau, F. Moutarde, W. Xi, & J. Yang, “Deep Learning for Hand Gesture Recognition on Skeletal Data”, In Automatic Face & Gesture Recognition (FG 2018), 13th IEEE International Conference on (pp. 106-113), IEEE, 2018.

9. [9] F. Başçiftçi, H. Sümbül, “Designing an expert system for detection of tuberculosis disease with logic simplification method”, e-Journal of New World Sciences Academy, NWSA Engineering Sciences, 1A0097, ISSN: 1308-7231, 5(3), 463-471, 2010.
10. [10] B. Ahmet, K. Yavuz, and K. Adem, “Bulanık uzman sistem yaklaşımı ile yeşil kart başvuru değerlendirme sistemi”, Atatürk Üniversitesi İktisadi ve İdari Bilimler Dergisi, Cilt: 24, Sayı: 1, 63-76, 2010.
11. [11] H. Sümbül, A.H. Yüzer, “Design of a fuzzy input expert system visual information interface for classification of apnea and hypopnea”, Multimedia Tools and Applications, 83(7), 21133-21152, 2024. https://dx.doi.org/10.1007/s11042-023-16152-9.
12. [12] A.B. Sargano, X. Gu, P. Angelov, et al., “Human action recognition using deep rule-based classifier”, Multimedia Tools and Applications, 2020, 30653–30667. https://doi.org/10.1007/s11042-020-09381-9.
13. [13] B. Choi, S. Kang, K. Jun, et al., “Rule-based soft computing for edge detection”, Multimedia Tools and Applications, 24819–24831, 2017. https://doi.org/10.1007/s11042-016-4329-7.
14. [14] W. Bi, F. Gao, A. Zhang, et al., “A framework for extended belief rule base reduction and training with the greedy strategy and parameter learning”, Multimedia Tools and Applications, 11127–11143, 2022. https://doi.org/10.1007/s11042-022-12232-4.
15. [15] A. Biswas, A. Adan, P. Haldar, D. Majumder, V. Natale, C. Randler, L. Tonetti, and S. Sahu, “Exploration of transcultural properties of the reduced version of the Morningness–Eveningness Questionnaire (rMEQ) using adaptive neuro-fuzzy inference system”, Biological Rhythm Research, 45(6), 955-968, 2014. DOI: 10.1080/09291016.2014.939442.
16. [16] E. Allam, H.F. Elbab, M.A. Hady, and S. Abouel-Seoud, “Vibration control of active vehicle suspension system using fuzzy logic algorithm”, Fuzzy Information and Engineering, 2(4), 361-387, 2010. https://doi.org/10.1007/s12543-010-0056-3.
17. [17] Ö.M. Soysal, S. Shirzad, and K. Sekeroglu, “Facial action unit recognition using data mining integrated deep learning”, 2017 International Conference on Computational Science and Computational Intelligence (CSCI), Las Vegas, NV, USA, 2017, pp. 437-443. doi: 10.1109/CSCI.2017.74.