Remote sensing image retrieval method based on feature selection and semi-supervised learning

Abstract

The invention discloses a remote sensing image retrieval method based on feature selection and semi-supervised learning. In the method, an optimal color feature and an optimal textural feature are selected respectively by utilizing a clustering method according to a minimum description length criterion and an improved Davies-Bouldin index; and then an appropriate semi-supervised learning method is selected according to the binarization weight of the optimal color feature and the optimal textural feature for carrying out remote sensing image retrieval. Compared with the traditional remote sensing image retrieval method, the invention not only can greatly improve the retrieval quality, but also can reduce the calculate quantity in the retrieval process and improve the retrieval speed.

Description

technical field [0001] The invention relates to an image retrieval method, in particular to a remote sensing image retrieval method. Background technique [0002] With the continuous development of remote sensing technology, the number of remote sensing images obtained every day has increased dramatically, and the research on automatic query and retrieval technology of remote sensing images has gradually become an urgent research topic. At present, scholars at home and abroad have proposed many methods for content-based remote sensing image retrieval (CBIR), such as texture features based on Gabor transform, combination of color features and texture features, fusion of texture features and spatial information, and similarity measurement of histogram features. method, and methods based on GIS spatial semantics. Zhu Bin proposed to use Gabor texture features to retrieve aerial images [Bin Zhu, Marshall R, Hsinchun C. Creating a large-scale content-based airphoto image digital...

AI Technical Summary

Problems solved by technology

[0004] Relevance feedback is the most commonly used learning strategy in CBIR. It relies on the human-computer interaction process, and the user continuously gives feedback. Its performance improves with the increase of the feedback sample set, but at the same time it will greatly increase the burden on the user.

Images