Comparative studies on similarity measures for remote sensing image retrieval

Similarity measure is usually used to study the method for guiding to select a similarity measure or a dissimilar degree between multi-source data, which is the basis of pattern recognition on spatial data. For it is the core technique in content-based image retrieval, similarity measure has very wide applications. In this work eight similarity measures are experimental investigated through some remote sensing image retrieval. The features extracted in the experiments are frequency histogram and cumulative histogram vectors. From the experiment results it can be found that X² statistical distance measure and cosine of the angle measure perform better than others. The results described in This work are of significance in applications to multi-source data analysis.