Classification of video data using Centroid Neural Network
Jaeyoung Kim, Dong-Chul Park, Dong-Min Woo · 2009
A classification method of video data using centroid neural network is proposed in this paper. The CNN algorithm is used for clustering the MPEG video data. In comparison with other conventional algorithms, The CNN requires neither a predetermined schedule for learning gain nor the total number of iterations for clustering. It always converges to sub-optimal solutions while conventional algorithms such as SOM may give unstable results depending on the initial learning gains and the total number of iterations. Experiments and results on several MPEG video data sets demonstrate that the classification model employing the CNN can archive improvements in terms of false alarm rate (FAR) over the models using the conventional k-means and SOM algorithms.