Research On Methods For Texture Feature-based Retrieval Of Remote Sensing Image

With the development of space technology, remote sensing technology, network and database, the data of remote sensing image that we can get is blooming in an astonishing speed. How to scan quickly and retrieve target efficiently in the region of interest from large remote sensing image database becomes the bottleneck of information extraction and share based on remote sensing image. The technique of content-based image retrieval provides a kind of powerful tool which can extract the information from the interest region of remote sensing image automaticaly, and it also becomes the hot spot at home and abroad. As the basical visualized characters, texture feature is used widely in the content-based retrieval of remote sensing images. Main research and concrete work include three aspects:1. This paper expounded and sumed up the key techniques of CBIR systematically, including the content-based feature description and feature extraction, and the similarity calculation of feature and the evaluation of CBIR performance etc.2. This paper have analyzed and studied the techonogies of texture-based retrieval from co-coccurrence matrix. For the shortage of traditional co-coccurrence matrix, the improved method by co-coccurrence matrix is propsed to use in the analysis of remote sensing image, the experimets indicate that the new method is robust to the invariance of scale and rotate.3. This paper proposed a new representation for texture feature on the wavelet algorithm, wich described the direction of the traditional wavelet tranform with more comprehensive information. After experimental analysis, it is proved the method with more feasibility and effectiveness.At the end of this paper, directions worthy of further research are pointed out.