A Geometric Model-Based Approach to Hand Gesture Recognition
Autor: | PAOLO ROSELLI, Vito Errico, Giovanni Saggio, Jean Vanderdonckt, Alexandre Calado, Nathan Magrofuoco |
---|---|
Přispěvatelé: | UCL - SSH/LouRIM - Louvain Research Institute in Management and Organizations, UCL - SST/IRMP - Institut de recherche en mathématique et physique |
Jazyk: | angličtina |
Rok vydání: | 2022 |
Předmět: |
explainable artificial intelligence (XAI)
training gesture recognition machine learning (ML) assistive technologies Settore ING-INF/01 gyroscopes algebra geometric algebra Computer Science Applications Human-Computer Interaction Accelerometers deep learning (DL) nearest neighbor classification (NNC) trajectory Control and Systems Engineering Electrical and Electronic Engineering Software |
Zdroj: | IEEE Transactions on Systems, Man, and Cybernetics: Systems, Vol. 52, no. 10, p. 6151-6161 (2022) |
Popis: | Arm-and-hand tracking by technological means allows gathering data that can be elaborated for determining gesture meaning. To this aim, machine learning (ML) algorithms have been mostly investigated looking for a balance between the highest recognition rate and the lowest recognition time. However, this balance comes mainly from statistical models, which are challenging to interpret. In contrast, we present μ C¹ and μ C², two geometric model-based approaches to gesture recognition which support the visualization and geometrical interpretation of the recognition process. We compare μ C¹ and μ C² with respect to two classical ML algorithms, k-nearest neighbor (k-NN) and support vector machine (SVM), and two state-of-the-art (SotA) deep learning (DL) models, bidirectional long short-term memory (BiLSTM) and gated recurrent unit (GRU), on an experimental dataset of ten gesture classes from the Italian Sign Language (LIS), each repeated 100 times by five inexperienced non-native signers, and gathered with wearable technology (a sensory glove and inertial measurement units). As a result, we achieve a compromise between high recognition rates (>90%) and low recognition times ( |
Databáze: | OpenAIRE |
Externí odkaz: |