Semi-supervised spectral clustering synthetic aperture radar (SAR) image segmentation method based on density reachable measure

Abstract

The invention discloses a semi-supervised spectral clustering synthetic aperture radar (SAR) image segmentation method based on density reachable measure, which mainly solves the problem that image segmentation accuracy is low in the prior art. The semi-supervised spectral clustering SAR image segmentation method includes: (1) inputting an SAR image to be segmented, and enabling all pixel points in the image to form a data set; (2) obtaining a density reachable relation between any two points in the data set; (3) constructing a similarity matrix based on density reachable area radius according to the density reachable relation; (4) adding paired constraint information in the obtained similarity matrix to construct a Laplace matrix, performing characteristic value decomposition on the Laplace matrix, and taking the front c characteristic vectors to construct a novel data set; and (5) labeling categories of data points of the novel data set obtained through clustering by using a K-means clustering method, and outputting a segmentation result graph of the SAR image. Compared with the prior art, the semi-supervised spectral clustering SAR image segmentation method based on the density reachable measure has the advantages of being insensitive to noise and high in segmentation accuracy and can be applied to SAR image segmentation.

Description

technical field [0001] The invention belongs to the technical field of image processing, relates to SAR image segmentation, is one of the key technologies for SAR image understanding and interpretation, and can be used for SAR image preprocessing. Background technique [0002] SAR image segmentation is an important step in the process of SAR image processing. The purpose of SAR image segmentation is to cluster different ground objects contained in SAR images into different classes according to the relationship between image pixels. Spectral clustering is an emerging clustering method in recent years. The idea of ​​this algorithm comes from the theory of spectral graph partitioning, and it is regarded as a multi-way partitioning problem of an undirected graph. The reason why spectral clustering is superior to traditional clustering algorithms is that it is not limited by the shape of the sample space and converges to the global optimal solution. Therefore, spectral clusterin...

AI Technical Summary

Problems solved by technology

Therefore, it is not limited to a standard global optimization function, and there are also some problems, such as the difficulty of determining parameters, and the inability to simultaneously discover clusters with uneven density distribution in the data set, etc.

[0007] The spectral clustering method mentioned above has the following shortcomings: 1. It is susceptible to noise and causes clustering errors; 2. The results for large data are not good or invalid; 3. The parameters are difficult to determine; 4. The density in the data set cannot be found at the same time Unevenly distributed clusters

Images