Proceedings of the IEEK Conference (대한전자공학회:학술대회논문집)
- 2000.07b
- /
- Pages.1049-1052
- /
- 2000
An Automatic Cut Detection Algorithm Using Median Filter And Neural Network ITC-CSCC'2000
- Jun, Seung-Chul (Department of Computer Science & Engineering) ;
- Park, Sung-Han (Department of Computer Science & Engineering)
- Published : 2000.07.01
Abstract
In this paper, an efficient method to find cut in the MPEG stream data is proposed. For this purpose, histogram difference and pixel difference is considered as a noise signal. The signal is then filtered out by a median filter to make the frame difference larger. The frame difference obtained in this way is classified into cut frame and non-cut frame by the 2-means clustering without using any threshold value. To improve the classification ratio, a back-propagation neural network is constructed, where outputs of 2-means clustering are used as the inputs of the network. The simulation results demonstrate the performance of the proposed methods.
Keywords