Feature vector or time-series – comparison of gestures representations in automatic gesture recognition systems
Journal Title: Challenges of Modern Technology - Year 2015, Vol 6, Issue 1
Abstract
In this paper, we performed recognition of isolated sign language gestures - obtained from Australian Sign Language Database (AUSLAN) – using statistics to reduce dimensionality and neural networks to recognize patterns. We designated a set of 70 signal features to represent each gesture as a feature vector instead of a time series, used principal component analysis (PCA) and independent component analysis (ICA) to reduce dimensionality and indicate the features most relevant for gesture detection. To classify the vectors a feedforward neural network was used. The resulting accuracy of detection ranged between 61 to 87%.
Authors and Affiliations
Katarzyna Barczewska, Wioletta Wójtowicz, Tomasz Moszkowski
Keywords
Related Articles
- EP ID EP206669
- DOI -
- Views 103
- Downloads 0
Spectral analysis of parametric two degreesof- freedom system
In this paper model of a vibrating system of two rotating, stressed to each other and periodically losing contact cylinders is presented. The model is described by two-degrees-of-freedom Hill's differential equations sys...
Short review on atmospheric aerosols source apportionment methods
Appropriate understanding of particulate matter emission sources is required to properly establish the policies aiming at the aerosols emitters’ elimi - nation. The article provides a short review on atmospheric aerosols...
Separation of nanoparticles and nanodroplets from air using fibrous filters
Separation of particles from gas stream is of great importance in many areas of human life. Air filtering materials have wide applications. They are used inter alia in ventilation and air conditioning systems, in cars to...
Architecture of higher education in Poland in the context of sustainable development
The beginning of the 21st century was in Poland a period of intense investment activity in the development of infrastructure for higher education. University campuses have the potential to become an excellent model of ar...
Citizens’ Participation in the Noise Action Planning
The complexity of noise mapping and action planning, the free interpretation of Article 8.7. (Action plans – Public Participation) and Article 9.2. (Information to the Public – Information about Noise Action Plans) of th...