Please use this identifier to cite or link to this item: http://idr.nitk.ac.in/jspui/handle/123456789/9977
Title: 2D-spectral estimation based on DCT and modified magnitude group delay
Authors: Sandeep, P.
Shreyamsha, Kumar, B.K.
Narasimhan, S.V.
Issue Date: 2013
Citation: Signal, Image and Video Processing, 2013, Vol.7, 5, pp.959-973
Abstract: This paper proposes two new 2D-spectral estimation methods. The 2D-modified magnitude group delay (MMGD) is applied to 2D-discrete Fourier transform (2D-DFT) for the first and to the analytic 2D-discrete Cosine transform for the second. The analytic 2D-DCT preserves the desirable properties of the DCT (like, improved frequency resolution, leakage and detectability) and is realized by a 2D-discrete cosine transform (2D-DCT) and its Hilbert transform. The 2D-MMGD is an extension from 1D to 2D, and it reduces the variance preserving the original frequency resolution of 2D-DFT or 2D-analytic DCT, depending upon to which is applied. The first and the second methods are referred to as DFT-MMGD and DCT-MMGD, respectively. The proposed methods are applied to 2D sinusoids and 2D AR process, associated with Gaussian white noise. The performance of the DCT-MMGD is found to be superior to that of DFT-MMGD in terms of variance, frequency resolution and detectability. The performance of DFT-MMGD and DCT-MMGD is better than that of 2D-LP method even when the signal to noise ratio is low. 2012 Springer-Verlag London Limited.
URI: 10.1007/s11760-011-0286-9
http://idr.nitk.ac.in/jspui/handle/123456789/9977
Appears in Collections:1. Journal Articles

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.