Synthetic aperture radar (SAR) image bionic recognition method based on sample generation and nuclear local feature fusion

Abstract

The invention provides a synthetic aperture radar (SAR) image bionic recognition method based on sample generation and nuclear local feature fusion and belongs to the field of image processing technologies and SAR target recognition. According to the method, a super complete training sample set is firstly constructed for training to obtain geometry manifold, then a sample to be recognized is recognized, specifically, each sample is firstly subjected to image denoising by a K-SVD dictionary learning method, and object region extraction is achieved by means of an object centroid method; and feature extraction is performed respectively by combining local phase quantization (LPQ) and a Gabor filtering method, feature fusion is performed, finally, classification is performed by covering of high-dimensional geometry manifold, and recognition is performed by a bionic mode. According to the SAR image bionic recognition method based on sample generation and nuclear local feature fusion, inhibiting effects of image coherent noises are obvious, SAR image features can be effectively extracted, the problem of the unstable extracted features, which is caused by changes of attitude angles of SAR images, is solved, the recognition accuracy is high, and the method has good robustness.

Description

technical field [0001] The invention belongs to the field of image processing technology and SAR target recognition, in particular to a SAR image bionic recognition method based on sample generation and nuclear local feature fusion, which can be applied to military and civilian target recognition. Background technique [0002] Synthetic Aperture Radar (SAR) has good application prospects in the fields of modern battlefield perception and ground military strikes because it can obtain ground battlefield data all-weather and all-weather, making automatic target recognition based on SAR images ( Automatic Target Recognition, referred to as ATR) has been paid more and more attention by researchers, and has gradually become one of the research hotspots at home and abroad. In the research of SAR target recognition, many research institutions at home and abroad are mostly based on the Moving and Stationary Target Acquisition and Recognition (MSTAR) database provided by the US DARPA / ...

AI Technical Summary

Problems solved by technology

The method of the invention can effectively remove the coherent noise interference in the SAR image, and overcome the problem of unstable feature extraction caused by the change of the attitude angle of the SAR image, thereby improving the correct recognition rate of the SAR image target recognition

Images