Remote sensing image retrieval method based on improved support vector machine relevance feedback

Abstract

The invention relates to a remote sensing image retrieval method based on improved support vector machine relevance feedback. The method comprises the following steps of: establishing a remote sensing image database, and selecting an image meeting a retrieval object from the remote sensing image database as a query image; performing remote sensing image feature extraction on the remote sensing image database to obtain feature vectors; calculating Euclidean distances between the feature vectors of images and the query image in the remote sensing image database based on the feature vectors, andreturning a given number of remote sensing images sequentially from short distances to long distances as initial retrieval results; and performing relevance feedback, namely evaluating the initial retrieval results, and finishing retrieval if the initial retrieval results are satisfactory. By the method, the problems of the conventional support-vector-machine-based relevance feedback algorithm about retrieval result sequencing, particularly the problems about classification and identification in a high-dimensional feature space are well solved, and remote sensing image retrieval accuracy and retrieval result sequencing rationality can be effectively improved; and the method can be used for a plurality of application fields related to remote sensing image retrieval.

Description

technical field [0001] The invention relates to the technical field of computer image retrieval, in particular to a remote sensing image retrieval method based on improved support vector machine correlation feedback. Background technique [0002] Content-based remote sensing image retrieval (Content-based Remote Sensing Image Retrieval, CBRSIR), the so-called "picture search", it is developed on the basis of content-based image retrieval (Content-based Image Retrieval, CBIR) A new media information retrieval technology. It expresses the content of the image by extracting the visual features (color, shape, texture, spectrum, etc.) in the remote sensing image. Extract information clues from media content, use approximate matching technology, and use relevant feedback as an effective means to achieve rapid retrieval in large databases. In order to meet the accuracy requirements of remote sensing image retrieval, relevant feedback technology must be added, from simple one-time...

AI Technical Summary

Problems solved by technology

[0009] In view of the problems in the field of remote sensing image retrieval and pattern recognition in the above-mentioned prior art, because the similarity measurement strategies of related feedback are often different, the results of the feedback retrieval have certain differences in content and order. The technical problem is to provide a remote sensing image retrieval method based on improved support vector machine correlation feedback, which not only improves the accuracy of remote sensing image retrieval, but also can reasonably sort the retrieval results.

Images