Title
Recognition of Human Actions Using Moment Based Features and Artificial Neural Networks
Abstract
This paper presents performance of view-based approach in automated recognition of pre-defined hand and gross body actions using artificial neural network. This approach represents motion by a static grey scale image template computed by collapsing the temporal components into the cumulative image-difference of frames. The seven invariant Hu moments are used as the feature vectors the performance of the system is tested, in real time, using feed forward multilayer perceptron (MLP) based on back propagation.
Year
DOI
Venue
2004
10.1109/MULMM.2004.1265015
MMM
Keywords
Field
DocType
artificial neural networks,cumulant,backpropagation,feature extraction,multilayer perceptron,object recognition,feed forward,artificial neural network,feature vector,gesture recognition,real time,back propagation
Computer vision,Feature vector,Pattern recognition,Computer science,Gesture recognition,Feature extraction,Time delay neural network,Multilayer perceptron,Artificial intelligence,Artificial neural network,Backpropagation,Cognitive neuroscience of visual object recognition
Conference
ISBN
Citations 
PageRank 
0-7695-2084-7
1
0.37
References 
Authors
2
4
Name
Order
Citations
PageRank
Arun Sharma110.37
Dinesh K. Kumar2839.17
Sanjay Kumar310.37
Neil McLachlan4163.33