SVM-relevance-feedback and Semantic-extraction-based RS Image Retrieval

The semantic gap between high-level human perception and low-level image features becomes the bottleneck in content-based remotely sensed image retrieval technology.To solve this problem,in this research,a human machine interaction(HMI) remotely sensed image retrieval system is built that combines semantic mining model and SVM-based relevance feedback method.The experiments indicate that this method can well narrow semantic gap and improve retrieval precision and recall.