Paper—Design of a Hand Pose Recognition System for Mobile and Embedded Devices Design of a Hand Pose Recognition System for Mobile and Embedded Devices https://doi.org/10.3991/ijes.v10i04.35163 Houssem Lahiani 1,2(*) , Mahmoud Neji 2,3 1 National School of Electronics and Telecommunications, University of Sfax, Sfax, Tunisia 2 Multimedia Information Systems and Advanced Computing Laboratory, Sfax, Tunisia 3 Faculty of Economics and Management of Sfax, University of Sfax, Sfax, Tunisia lahianihoussem@gmail.com Abstract—Today, smart devices such smart watches and smart cell phones are becoming ever-present in all felds that infuence the quality of life of the modern people. These on-board systems have revolutionized the behavior of human beings and especially their way of communicating. In this context and to improve the experience of using these devices, we aim to develop a system that recognizes hand poses in the air by a smart device. In this work, the sys- tem is based on Histogram of Oriented Gradient (HOG) features and Support Vector Machine (SVM) classifer. The impact of using HOG and SVM on mobile devices is studied. To carry out this study, we used an improved version of the “NUS I” dataset and obtained a recognition rate of approximately 94%. In addi- tion, we conducted run speed experiments on various mobile devices to study the impact of this task on this embedded platform. The main contribution of this work is to test the impact of using the HOG descriptor and the SVM classifer in terms of recognition rate and execution time on low-end smartphones. Keywords—android, HOG, SVM, gesture detection, run speed 1 Introduction Today, smart devices such as smart watches and smart cell phones are becoming ever-present in all felds that infuence the quality of life of the modern human being. We could use them for working, playing, shopping [1], and even in the education we use now mobile learning [2]. The majority of today’s smartphones have a touch screen. This sort of screen has enhanced the way we interact with mobile devices, but it is expected that future mobile devices, such as Google glasses and smart watches, would incorporate a more inter- active and intuitive interaction interface. Some of these devices are equipped with a voice recognition system to control them, but this solution may not be effective in noisy places. Moreover, this voice recognition-based solution is not suitable for the deaf and dumb people, which makes in-air gestures recognition a crucial solution to control these devices. Indeed, many complex problems arise for the development of such a system, and which make the realization of an interactive system to interact with mobile iJES ‒ Vol. 10, No. 04, 2022 17