10th International Multimedia Modelling Conference, 2004. Proceedings.
This paper presents a method for hand gesture classification using a view-based approach for repr... more This paper presents a method for hand gesture classification using a view-based approach for representation and Artificial Neural Network for classification. This approach uses a cumulative imagedifference technique in which time between the sequences of images is implicitly captured in the representation of action. This results in the construction of Temporal History Templates (THT). These images are used to compute the 7 Hu image moments, which are invariant to scale, rotation and translation. The classification is then performed using back propagation based multilayer perceptron (MLP) Artificial Neural Network (ANN). The preliminary experiments show that such a system can classify human hand gestures with a classification accuracy of 96%. Motivation of the work is to build a system for person identification based on this technique.
ABSTRACT Uncertainties in local solar radiation, ambient temperature and thermal load data have b... more ABSTRACT Uncertainties in local solar radiation, ambient temperature and thermal load data have been one of the major factors limiting the reliability and efficiency of solar thermal hybrid systems. In the present paper, moving average auto regressive exogenous (ARX) model based reasoning has been mooted and modified to include moving average method, as an effective tool for predictions of these data. The results show that the method is quite robust and is capable of predicting fairly accurate results, which would make these systems more viable in areas where meteorological data are not available or vague.
10th International Multimedia Modelling Conference, 2004. Proceedings.
This paper presents a method for hand gesture classification using a view-based approach for repr... more This paper presents a method for hand gesture classification using a view-based approach for representation and Artificial Neural Network for classification. This approach uses a cumulative imagedifference technique in which time between the sequences of images is implicitly captured in the representation of action. This results in the construction of Temporal History Templates (THT). These images are used to compute the 7 Hu image moments, which are invariant to scale, rotation and translation. The classification is then performed using back propagation based multilayer perceptron (MLP) Artificial Neural Network (ANN). The preliminary experiments show that such a system can classify human hand gestures with a classification accuracy of 96%. Motivation of the work is to build a system for person identification based on this technique.
ABSTRACT Uncertainties in local solar radiation, ambient temperature and thermal load data have b... more ABSTRACT Uncertainties in local solar radiation, ambient temperature and thermal load data have been one of the major factors limiting the reliability and efficiency of solar thermal hybrid systems. In the present paper, moving average auto regressive exogenous (ARX) model based reasoning has been mooted and modified to include moving average method, as an effective tool for predictions of these data. The results show that the method is quite robust and is capable of predicting fairly accurate results, which would make these systems more viable in areas where meteorological data are not available or vague.
Uploads
Papers by Sanjay Kumar D