A Similarity Metric for Retrieval of Compressed Objects: Application for Mining Satellite Image Time Series
Issue No.04 - April (2008 vol.20)
This paper adresses the problem of building an index of compressed object data-base. We introduce an informational similarity measure based on coding length of two part codes. Then, we present a methodology to compress the data-base by taking into account inter-object redundancies and by using the informational similarity measure. The method produces an index included in the code of the data-volume. This index is built such that it contains the minimal sufficient information to discriminate the data-volume objects. Then, we present an optimal two part coder for compressing spatio-temporal events contained in Satellite Image Time Series (SITS). The two part coder allows us to measure similarity and, then, to derive an optimal index of SITS spatio-temporal events. The resulting index is representative of the SITS information content and enables queries based on information content.
IIndex Generation, Model classification, Remote sensing, Clustering, Pattern Recognition, Statistical, Time-varying imagery, Models, Compression (Coding), Model-based coding, Texture, Content Analysis and Indexing, Information Search and Retrieval, Information theory
Lionel Gueguen, Mihai Datcu, "A Similarity Metric for Retrieval of Compressed Objects: Application for Mining Satellite Image Time Series", IEEE Transactions on Knowledge & Data Engineering, vol.20, no. 4, pp. 562-575, April 2008, doi:10.1109/TKDE.2007.190718