Jung Eun Yung, Lee Dong Seop, Shin Sung Yoon, Jeon Keun Hwan, Bae Seok Chan, Lee Yang Weon

The Transactions of the Korea Information Processing Society (1994 ~ 2000), Vol. 6, No. 2, pp. 282-291, Feb. 1999
10.3745/KIPSTE.1999.6.2.282,   PDF Download:

Abstract

In order to construct the News Video Database System, cut detection technique is very important. In general, the color histogram, x2 histogram or Bin-to-Bin Difference(B2B) techniques are mainly using for the scene partitioning. In the paper, we propose the efficient algorithm that is applied the weight in terms of NTSC standard to cut detection. This algorithm is able to reduce the time of acquiring and comparing histogram using by separate calculation of RGB for the color histogram technique. And it also provide the efficient selection method of threshold value by emphasis of the difference in the x2 histogram technique. For the performance evaluation of this algorithm, we select and use the news videos of KBS, MBC, SBS, CNN and NHK as experimental domains. By the result of experiment domains. By the result of experiment, we present the proposed algorithm is more efficient for cut detection than the previous methods, and that the basis for the automatic selection of threshold values.

Statistics
Cite this article