Abstract | ||
---|---|---|
The quality of codebook is the determinant factor in BoW-based copy detection strategies. However, most of the adopted codebook construction algorithms are derived from image retrieval or object recognition, which neglect the robustness in partitioning original features and copy features (especially those with serious transformations) into the same group. To deal with this problem, we have developed an Incremental Clustering algorithm to construct a robust codebook. Unlike many existing algorithms which need loading the entire data into memory, our algorithm process data incrementally and improve the quality by transferring data from a global view. In addition, we propose a codebook evaluation scheme by simulating copy and non-copy pairs. Our experimental results show that our approach attains a high precision in copy pairs, which demonstrates the robustness of our codebook. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1109/SSIAI.2012.6202489 | SSIAI |
Keywords | Field | DocType |
noncopy pairs,cbcd systems,content-based copy detection systems,pattern clustering,bow,incremental clustering,bow-based copy detection strategies,copy features,video copy detection,codebook construction,copy pairs,codebook evaluation scheme,codebook quality,image retrieval,video coding,object detection,object recognition,determinant factor,incremental clustering based codebook construction,video retrieval,feature extraction,visualization,databases,robustness,clustering algorithms | Object detection,Computer vision,Linde–Buzo–Gray algorithm,Pattern recognition,Computer science,Image retrieval,Feature extraction,Robustness (computer science),Video copy detection,Artificial intelligence,Cluster analysis,Codebook | Conference |
ISBN | Citations | PageRank |
978-1-4673-1829-7 | 1 | 0.36 |
References | Authors | |
2 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Huamin Ren | 1 | 44 | 5.62 |
Heri Ramampiaro | 2 | 154 | 20.46 |
Yongdong Zhang | 3 | 7 | 2.20 |
Shouxun Lin | 4 | 963 | 56.20 |