Karate Kata Style Classification Using Pose Landmarks and Deep Learning

The Faculty of Computer Science at October University for Modern Sciences and Arts (MSA University) would like to congratulate the students, Mahmoud Hossa and Farida Sherif as they soared to great heights with their groundbreaking research.

Among 316 authors and 220 papers, their work “Karate Kata Style Classification Using Pose Landmarks and Deep Learning” our Computer Scientists secured the 2nd Place Best Paper Award at the 5th Novel Intelligent and Leading Emerging Sciences Conference (NILES 2023).

Their innovative approach, employing deep learning techniques to classify Karate Kata styles, reflects their dedication to enhancing classification models. By manually curating a suitable dataset and utilizing deep learning methods to process player pose landmarks, they’ve paved the way for improved classification with the use of Long Short Term Memory (LSTM) neural networks.

Congratulations to our students for their remarkable work.