SAR image classification method based on united sparse representation

Abstract

The invention discloses an SAR image classification method based on united sparse representation. The SAR image classification effect is improved based on an existing sparse representation method. According to the implementation process, the SAR image classification method comprises the steps that (1) SAR images to be trained are input, the features of the SAR images are extracted, and similar sets are classified; (2) united sparse representation is conducted on the similar set of each class of the SAR images, and a small dictionary and sparse coefficients of each similar set are obtained correspondingly; (4) SAR images to be tested are input, the features of the SAR images to be tested are extracted, feature vectors are projected on the small dictionary, and coefficients of the tested images are obtained; (5) the coefficients of the tested images and the sparse coefficients of all the trained images are matched, a set of most matched coefficients in the sparse coefficients are found, and the marked category of the set of most matched coefficients serves as the category of the SAR images to be tested. Compared with a traditional KNN and classic sparse representation classification method, the accuracy of even texture image and SAR image classification is greatly improved.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to a SAR image classification method based on joint sparse representation, which can be used for SAR image classification. Background technique [0002] The classification of synthetic aperture radar SAR images is a key step to realize the automatic processing of SAR images and the premise of further interpretation of SAR images. It is a typical example of extracting the front-end part of the interpretation system separately as a specific application. Synthetic Aperture Radar (SAR) is a high-resolution remote sensing imaging radar, which has the characteristics of all-weather, all-time, multi-band, multi-polarization, variable viewing angle, strong penetrating ability and high resolution. It can not only observe terrain and landform in more detail and accurately, obtain surface information, but also collect underground information through certain surface and natural vegetatio...

AI Technical Summary

Problems solved by technology

[0004] The SRC method is applied to the SAR image classification after feature extraction, and the effect is good, but the category information of the training samples is not fully utilized in the training process, that is, the process of calculating the sparse representation coefficient.

Using the traditional KNN method to classify SAR graphics, the effect achieved is not ideal

Images