Learn More
A learning algorithm for the principal component analysis is developed based on the least-square minimization. The dual learning rate parameters are adjusted adaptively to make the proposed algorithm capable of fast convergence and high accuracy for extracting all principal components. The proposed algorithm is robust to the error accumulation existing in(More)
—A new method of phase error estimation that utilizes the weighted least-squares (WLS) algorithm is presented for synthetic aperture radar (SAR)/inverse SAR (ISAR) autofocus applications. The method does not require that the signal in each range bin be of a certain distribution model, and thus it is robust for many kinds of scene content. The most(More)
—In this paper, we propose a new method to estimate synthetic aperture radar interferometry (InSAR) interferometric phase in the presence of large coregistration errors. The method takes advantage of the coherence information of neighboring pixel pairs to automatically coregister the SAR images and employs the projection of the joint signal subspace onto(More)
A dynamical system for computing the largest eigenpair of a given positive matrix is introduced. Certain qualitative properties of the proposed system are analyzed in detail. The authors' results suggest that the weight-bounding term in PCA algorithms for extracting the first principal component could assume a class of forms.