Image target identification method based on curvelet domain bilateral two-dimension principal component analysis

Abstract

The invention discloses a synthetic aperture radar (SAR) image target identification method based on curvelet domain bilateral two-dimension principal component analysis. The method specifically comprises the following steps of: inputting images of a training sample and a test sample, and normalizing the sample images; performing curvelet transformation on the normalized samples, and extracting low-frequency sub-band coefficients of each sample which is transformed; acquiring left and right projection matrixes of characteristics according to the obtained low-frequency sub-band coefficients of the training sample; acquiring characteristic values of the training sample and the test sample by using the left and right projection matrixes which are obtained; and classifying the characteristics of the test sample by using a nearest neighbor classification method, and thus obtaining a final identification result. Compared with the prior art, the method has the advantages that the dimensionality of the characteristics is effectively reduced, high correct identification rate can be obtained, an implementation method is simple, and identification time is effectively shortened.

Description

technical field [0001] The invention relates to a method for recognizing a synthetic aperture radar (SAR) image target, which belongs to the technical field of radar image recognition, and in particular relates to a bilateral two-dimensional principal component analysis method using a curve wave domain and applying it to a synthetic aperture radar (SAR) A method for object recognition in images. Background technique [0002] SAR image target recognition technology has received extensive attention from researchers in recent decades, and a variety of target recognition methods have been proposed. Generally speaking, they can be divided into three categories: methods based on template matching, methods based on the combination of kernel and support vector machine methods and model-based recognition methods. One of the most widely used is a class of recognition methods based on template matching. In 1998, T.Ross et al [T.Ross, S.Worrell, V.Velten, J.Mossing, M.Bryant. Standard...

AI Technical Summary

Problems solved by technology

However, the principal component analysis method and its kernelization method need to straighten the two-dimensional image into a one-dimensional column vector for processing, which will bring about the problem of "dimension disaster" and bring inconvenience to practical applications.

To this end, Yang proposed a two-dimensional principal component analysis method [Yang J, Zhang D, Frangi A F, et al. Two-dimensional PCA: a new approach to appearance based face representation and recognition [J]. IEEE Transaction on Pattern Analysis Machine Intelligence,2004,26(1):131-137], this method can be directly applied to two-dimensional images, effectively retaining the two-dimensional spatial structure information of the original image, and its covariance matrix is ​​more accurate and effective, but due to the right projection , this method only removes the correlation between row pixels, and the obtained feature dimension is still very large, which is not conducive to the subsequent target recognition and classification

In order to overcome the problems of the feature extraction method in the aforementioned literature, Kong et al. proposed a bilateral two-dimensional principal component analysis method [Kong H, Li X, Wang L, et al.Generalized 2D principal component analysis[C].IEEE International Joint Conference on Neural Networks,2005,V1,108-113], this method effectively reduces the feature dimension by projecting the samples left and right, but this method does not take into account the nonlinear characteristics of synthetic aperture radar, which is not conducive to SAR image targets recognition effect

Images