The Cut Detection Issue in the Animation Movie Domain

@article{Ionescu2007TheCD,
  title={The Cut Detection Issue in the Animation Movie Domain},
  author={Bogdan Ionescu and Patrick Lambert and Didier Coquin and Vasile Buzuloiu},
  journal={Journal of Multimedia},
  year={2007},
  volume={2},
  pages={10-19}
}
In this paper we are proposing an improved cut detection algorithm adapted to the animation movies domain. A cut is the direct concatenation of two different shots and produces an important visual discontinuity in the video stream. As color is one major feature of the animation movies (each movie has its own particular color palette) the proposed approach performs by thresholding the distance values obtained between frame color histograms. To overcome the difficulty raised by the peculiarity of… CONTINUE READING

13 Figures & Tables

Extracted Numerical Results

  • The histogram methodleads to the lower recall ratio, 88.63%, thus the smallest number of good detections, while the motion methodachieved the best recall ratio, 94.53%, but with a higher false detection ratio, precision 89.39%.
  • The recall obtained with thehistogram methodwas improved of 4%, thus a number of 125 cuts were additionally successfully detected, while the precision of © 2007 ACADEMY PUBLISHER the motion methodwas improved of5.5%, thus 178 cuts were additionally successfully detected. Moreover, using the proposed cut detection in conjunction with the SCC detection procedure, the precision was up to96%and thus improved of 1% (see Table III).
  • The proposed adaptive thresholding approach provided good detection results, thus we have achieved a global precision ratio of 91% and a recall ratio of 90.5%.
  • The obtained recall and precision are both above 92%, which is an improvement of around 3% (more than 100 cuts). Also, by using the proposed method in conjonction with the SCC detection, the precision ratio was improved by 1%.

Topics