Multi-objective sar image segmentation method based on fair feature integration

Abstract

The invention discloses a multi-objective SAR image segmentation method based on feature fair integration, the realization steps of which are: (1) reading in a synthetic aperture radar SAR image; (2) extracting a grayscale feature map; (3) extracting grayscale co-occurrence Matrix feature map; (4) synthetic total feature map; (5) normalization processing; (6) calculation of superpixel features; (7) population initialization; (8) feature fair integration; (9) calculation of individual fitness in the population value; (10) optimize the fitness value; (11) segment the image. The invention adopts multi-feature fair integration, reduces the misclassification rate of image segmentation, and improves the accuracy of image segmentation.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to a multi-target Synthetic Aperture Radar (SAR) image segmentation method based on fair integration of features in the technical field of image segmentation. The invention can be used to extract multiple features of the synthetic aperture radar SAR image, cluster the extracted features by multi-target clustering, and obtain the final segmentation map from the labels generated by the clustering. Background technique [0002] Image segmentation is the technology and process of dividing an image into several specific regions with unique properties and extracting objects of interest. It is a key step in advanced image manipulations such as image analysis, pattern recognition, and computer vision. In recent years, with the application of statistical theory, fuzzy set theory, and machine learning theory in the field of image segmentation, many new methods and ideas have b...

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that it only considers the grayscale features of the synthetic aperture radar SAR image, and the grayscale features of the SAR image are deceptive and easily lead to wrong segmentation, so that the present invention effectively enhances the segmentation effect

The disadvantage of this method is that because this method uses the fuzzy C-means clustering algorithm for clustering, and the calculation of similarity in the fuzzy C-means algorithm uses Euclidean distance, the disadvantage of Euclidean distance calculation fusion feature similarity is that it does not distinguish Treating each feature in the fusion feature will make the feature with high dimensionality dominate and weaken the feature with small dimensionality, so that the interaction between different features will cause serious loss of edge information and poor detail retention, which will reduce the accuracy of image segmentation. Spend

Images