We propose radar image classification via pseudo-Zernike moments based sparse representations. We exploit invariance properties of pseudo-Zernike moments to augment redundancy in the sparsity representative dictionary by introducing auxiliary atoms. We employ complex radar signatures. We prove the validity of our proposed methods on the publicly available moving and stationary target acquisition and recognition dataset.


    Access

    Download


    Export, share and cite



    Title :

    Pseudo-Zernike Moments Based Sparse Representations for SAR Image Classification


    Contributors:


    Publication date :

    2019-04-01


    Size :

    1256318 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Neural Network Image Recognition by Zernike and Pseudo-Zernike Moments

    Sosulin, Y. G. / Dung, T. C. | British Library Online Contents | 2003


    Efficient computation of Zernike and Pseudo-Zernike moments for pattern classification applications

    Papakostas, G. A. / Boutalis, Y. S. / Karras, D. A. et al. | British Library Online Contents | 2010


    On the accuracy of image normalization by Zernike moments

    Yang, Z. / Fang, T. | British Library Online Contents | 2010


    On the computational aspects of Zernike moments

    Wee, C. Y. / Paramesran, R. | British Library Online Contents | 2007


    Numerical error analysis in Zernike moments computation

    Papakostas, G. A. / Boutalis, Y. S. / Papaodysseus, C. N. et al. | British Library Online Contents | 2006