Title :
Touch-Based Gesture Recognition for Human-Based Interfaces
Author :
Nicolaescu, Alexandru ; Mocanu, Irina
Author_Institution :
Comput. Sci. Dept., Univ. Politeh. of Bucharest, Bucharest, Romania
Abstract :
This paper presents a method for touch-based gesture recognition that can be used in human-centered interfaces for ambient intelligence applications. Gestures are associated with shapes and they are represented using Fourier coefficients. Neural Networks, Decision Trees, Naïve Bayes and a set of classifiers (based on Linear Discriminant Analysis) are tested for gesture recognition. All these methods are evaluated based on accuracy, training and recognition time. Also an application controlled by user using touch-based gestures is implemented.
Keywords :
Bayes methods; Fourier analysis; ambient intelligence; decision trees; gesture recognition; haptic interfaces; neural nets; Fourier coefficients; Naive Bayes; ambient intelligence applications; decision trees; human-based interfaces; human-centered interfaces; linear discriminant analysis; neural networks; touch-based gesture recognition; Accuracy; Decision trees; Gesture recognition; Neural networks; Shape; Testing; Training; Fourier descriptors; Neural Networks; human computer interaction; touch-based gestures;
Conference_Titel :
Control Systems and Computer Science (CSCS), 2015 20th International Conference on
Conference_Location :
Bucharest
Print_ISBN :
978-1-4799-1779-2
DOI :
10.1109/CSCS.2015.78
