Option for optimal extraction to indicate recognition of gestures using the self-improvement of the micro genetic algorithm

Sabri, Bassam Talib; Yaseen AL-Falahi, Noaman Ahmed; Salman, Isam Adil

doi:10.22075/ijnaa.2021.5375

Option for optimal extraction to indicate recognition of gestures using the self-improvement of the micro genetic algorithm

Document Type : Research Paper

Authors

Bassam Talib Sabri ¹

Noaman Ahmed Yaseen AL-Falahi ²

Isam Adil Salman ³

¹ Department of Business Information Technology, College of Business Informatics, University of Information Technology and Communications, Baghdad, Iraq

² Director of Price Control and Service Quality Department, Chief programmer, Iraqi Ministry of Communications, Baghdad, Iraq

³ Associate Director of the Software Department, Senior chief of Programs, Iraqi Ministry of Communications, Baghdad, Iraq

10.22075/ijnaa.2021.5375

Abstract

The hearing-impaired community uses gestures to communicate. Gestures can also be used in interactions between man and computer. However, gestures become increasingly complicated in a comparatively complex environment. A recognition algorithm with a choice of function based on the improved genetic algorithm is proposed to improve the ability to identify gestures. The recognition process includes retailing, extraction, and feeding functions before classifying the neural network. After learning gestures, the proposed method is compared with traditional methods that use the classic genetic algorithm. The proposed method demonstrates the effect of optimization and sensitivity of the function.

Keywords

adaptive filter

feature extraction

genetic algorithm

sign language recognition

speeded-up robust feature (SURF)

[1] M. Abid, E. Petriu and E. Amjadian, Dynamic sign language recognition for smart home interactive application
using stochastic linear formal grammar, IEEE Trans. Instrum. Measur. 11 (2015) 596–605.
[2] F. Ciaramello and S. Hemami, A computational intelligibility model for assessment and compression of American
sign language video, IEEE Trans. Image Proc. 24 (2011) 3014–3027.
[3] J. Galka, M. Masior and M. Zaborski, Inertial motion sensing glove for sign language gesture acquisition and
recognition, Expert Syst. Appl. 15 (2016) 6310–6316.
[4] H. Hikawa and K. Kaida, Novel FPGA implementation of hand sign recognition system with SOMHebb classiier,
IEEE Trans. Circ. Syst. Video Techn. 1 (2016) 153–166.
[5] R. Kaluri and P. Ch, An overview on human gesture recognition, Int. J. Pharmacy Tech. 28 (2016) 12037–12045.
[6] V. Kosmidou and L. Hadjileontiadis, Sign language recognition using intrinsic-mode Sample entropy on sEMG
and accelerometer data, IEEE Trans. Biomed. Engin. 12 (2009) 2879–2890.
[7] J. Lichtenaue and E. Hendriks, language recognition by combining statistical DTW and independent, IEEE Trans.
Pattern Anal. Machine Intel. 5 (2008) 2040–2046.
[8] R. Madeo, S. Peres and C. Lima, Gesture phase segmentation using support vector ma- chines, Expert Syst. Appl.
10 (2016) 100–115.
[9] S. Mitra and T. Acharya, Gesture recognition, IEEE Trans. Syst. Man. Cyber., Part C. 5 (2007) 311–324.
[10] K. Rajesh and R. Pradeep, Sign gesture recognition using modified region growing algorithm and adaptive genetic
fuzzy classifier, Int. J. Intel. Engin. Syst. 24 (2016) 471-484.
[11] G. Samra and F. Khalefah, Localization of license plate number using dynamic image processing techniques and
genetic algorithms, IEEE Trans. Evolut. Comput. 2 (2014) 244–257.
[12] T. Shanableh, K. Assaleh and M. Rousan, Spatio- temporal feature-extraction techniques for isolated gesture
recognition in Arabic sign language, IEEE Trans. Syst. Man. Cyber. Part B. 3 (2007) 641–650.
[13] T. Tuytelaars and K. Mikolajczyk, Local invariant feature detectors: A survey, Found. Trends Comput. Graph.
Vis.15 (2008) 177–280.