Wessa, ErinyAshraf, AbdelazizAtia, Ayman2022-04-072022-04-072021-12https://doi.org/10.1109/ICECET52533.2021.9698656http://repository.msa.edu.eg/xmlui/handle/123456789/4907ScopusKickboxing is a combat sport, based on kicking, punching, Knee and elbow strikes and defence moves. Every kickboxing technique needs to be preformed a specific way, As there is correct postures and wrong postures to every technique. In this paper, we offer a system that can facilitate the beginners trainees to learn kickboxing. The system uses a camera to estimate poses and then, classify them into 'correct techniques' and their common mistakes or 'wrong pose' using ANN. Live feedback is offered by the system. Whenever the classifier recognize a wrong pose, a message is shown to indicate how to correct the posture. Our hypothesis is that, when trainees have the ability to see and recognize their wrong posters, they learn faster. We evaluate the progress of the trainees based on the time it takes to complete a simple kickboxing exercise. Two types of experiments were conducted. The first calculated the progress of trainees everyday, the other calculated the progress of trainees through three training sessions in the span on two hours. Our results show that time taken by users to preform the moves decrease with each time they use our system. This paper focuses on 3 kickboxing techniques, which are slipping, jab and front kick. © 2021 IEEE.en-USclassificationKickboxingNeural Networkspose estimationArticlehttps://doi.org/10.1109/ICECET52533.2021.9698656