Vanderdonckt, JeanRucquoy, AlexandreAlexandreRucquoy2025-02-042025-02-042020https://dial-mem.test.bib.ucl.ac.be/handle/123456789/22984In our modern societies, human computer interactions became ubiquitous. A critical area of research in this subject is the ability, for an artificial intelligence, to recognize gestures performed by humans. There are many different approaches, each approach also having many different solutions and algorithms. The main objective of this work is to offer a tool that is able to benchmark different algorithms that perform 2D stroke gesture recognition, a particular sub-type of gestures, mostly using pattern matching techniques. Our solution is a simple web application, focused on ease of maintenance and extension. We hope that it will be of some use for researchers who want to perform benchmarks of said algorithms, or that it will serve as baseline for further works in the domain of gesture recognition. Since some parts of our application are related to work that is yet to be released, the code of our application is not, as of June 2020, publicly available online. You can, however, ask permission from either Prof. Vanderdonckt or Mr. Magrofuoco to have access to the sources.HCIStroke-gesture recognitionBenchmarkingtext::thesis::master thesisthesis:25132