A sample-based hierarchical adaptive K-means clustering method for large-scale video retrieval

Finding useful patterns in large datasets has attracted considerable interest recently, and one of the most widely studied problems in this area is the identification of clusters in a multi-dimensional dataset. This paper introduces a sample-based hierarchical adaptive K-means (SHAKM) clustering algorithm for large-scale video retrieval. To handle large databases efficiently, SHAKM employs a multilevel random sampling strategy. Furthermore, SHAKM utilises the adaptive K-means clustering algorithm to determine the correct number of clusters and to construct an unbalanced cluster tree. Furthermore, SHAKM uses the fast labelling scheme to assign each pattern in the dataset to the closest cluster. To evaluate the proposed method, several datasets are used to illustrate its effectiveness. The results show that SHAKM is fast and effective on very large datasets. Furthermore, the results demonstrate that the proposed method can be used efficiently and successfully for a project on content-based video copy detection. (C) 2013 Elsevier B.V. All rights reserved.