Paper Info
Title
Robust learning-based TV commercial detection
Abstract
A robust learning-based TV commercial detection approach is proposed in this paper. Firstly, a set of basic features that facilitate distinguishing commercials from general program are analyzed. Then, a series of context-based features, which are more effective for identifying commercials, are derived from these basic features. Next, each shot is classified as commercial or general program based on these features by a pre-trained SVM classifier. And last, the detection results are further refined by scene grouping and some heuristic rules. Experiments on around 10-hour TV recordings of various genres show that the proposed scheme is able to identify commercial blocks with relatively high detection accuracy.
Year
DOI
Venue
2005
10.1109/ICME.2005.1521382
ICME
Keywords
Field
DocType
commercial block identification,television broadcasting,learning (artificial intelligence),learning-based tv commercial detection,context-based feature,tv recording,scene grouping,video recording,feature extraction,image classification,support vector machine,pretrained svm classifier,heuristic rules,support vector machines,digital video broadcasting,animation,layout,robustness,learning artificial intelligence,databases,generic programming
Computer science,Robustness (computer science),Artificial intelligence,Digital Video Broadcasting,Contextual image classification,Broadcasting,Computer vision,Heuristic,Pattern recognition,Support vector machine,Feature extraction,Animation,Machine learning
Conference
ISBN
Citations 
PageRank 
0-7803-9331-7
35
1.64
References 
Authors
6
3
Name
Order
Citations
PageRank
Xian-Sheng Hua16566328.17
Lie LU21840134.64
Hong-Jiang ZHANG3173781393.22