A New Semantic Method for Image Retrieval

Abstract

In this paper, a multi-level image representation model is developed and used to mine semantic feature hidden in the original remote sensing image. This model is consisted of three levels: region level, region feature level and semantic level. The first two levels aim at represent image content by using region feature. Semantic level aims at extracting hidden semantic feature. At last, interested part and uninterested part method is used to improve the retrieval precision. Experiment shows that this method can well improve the accuracy of the retrieval result.