SAR image classification method and device based on hierarchical automatic encoder

Abstract

The invention provides a SAR image classification method and device based on a hierarchical automatic encoder, the method comprising the steps of: amplifying a sample of SAR images through a generalized regularized automatic encoder model; establishing a hierarchical automatic encoder network model according to the generalized regularized automatic encoder model; inputting the amplified sample ofthe SAR images into the hierarchical automatic encoder network model so that the hierarchical automatic encoder network model encodes the input samples; inputting the feature codes output from the hierarchical automatic encoder network model to a classifier, and classifying the amplified sample of the SAR images by the classifier. The technical scheme of the invention realizes the full training ofthe depth network through the amplification of the SAR image samples and improves the accuracy of the SAR image classification. By establishing a hierarchical automatic encoder network model to classify the input samples, the adaptability of SAR image samples is improved.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a SAR image classification method and device based on a hierarchical automatic encoder. Background technique [0002] With the development of information technology, image data has increased rapidly, and the demand for image processing has also greatly increased or decreased. Image classification is mainly to extract specific features in the image, characterize the information of the image through specific features, and then classify graphics according to the extracted specific features. [0003] At present, convolutional neural networks have been used for target recognition and classification in SAR (Synthetic Aperture Radar) images, and convolutional neural networks are effective for large data sets of SAR images. However, in actual use, the samples of SAR images are very limited. Sparse, therefore, a small number of samples extracted from large-scene SAR images simpl...

AI Technical Summary

Problems solved by technology

[0003] At present, convolutional neural networks have been used for target recognition and classification in SAR (Synthetic Aperture Radar) images, and convolutional neural networks are effective for large data sets of SAR images. However, in actual use, the samples of SAR images are very limited. Sparse, therefore, a small number of samples extracted from large-scene SAR images simply cannot satisfy the sufficient training of deep networks, resulting in a decrease in the classification accuracy of SAR images

Images