Title :
Detecting Cartoons: Automatic Video Genre Classification
Author :
Chen Fen ; Lai Maosheng ; Ye Zhining
Author_Institution :
Dept. of Inf. Manage., Nanjing Univ. of Sci. & Technol., Nanjing, China
Abstract :
This article shows the improvement of automatic cartoon classification. Two new visual features - color component and color kind based on region segmentation - are proposed. Compared to traditional HSV color histogram and texture, experiment using the two new features can achieve better result, with less dimensions and higher mining efficiency.
Keywords :
data mining; image classification; image segmentation; object detection; video signal processing; automatic cartoon classification; automatic video genre classification; cartoons detection; color component; color kind; high mining efficiency; region segmentation; Feature extraction; Histograms; Image color analysis; Pixel; Support vector machines; Training; Visualization;
Conference_Titel :
Management and Service Science (MASS), 2010 International Conference on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-5325-2
Electronic_ISBN :
978-1-4244-5326-9
DOI :
10.1109/ICMSS.2010.5576551
