Please use this identifier to cite or link to this item:
Title: SAR Image Registration Using An Improved Anisotropic Gaussian-SIFT Algorithm
Authors: Paul, Sourabh
Pati, Umesh C
Keywords: Synthetic Aperture Radar (SAR)
Improved Anisotropic Gaussian-Scale Invariant Feature Transform (IAGSIFT)
Gaussian-Gamma-Shaped Bi-Window (GGS-BW)
Issue Date: Dec-2017
Citation: 14th IEEE India Council International Conference (INDICON) 2017, IIT Roorkee, Roorkee, India, 15 - 17 December, 2017
Abstract: An Improved Anisotropic Gaussian-Scale Invariant Feature Transform (IAG-SIFT) algorithm is proposed to register the Synthetic Aperture Radar (SAR) images. The standard SIFT algorithm generates isotropic Gaussian scale space which blurs lots of details in the image. The Anisotropic Scale Space (ASS) can preserve more details than the isotropic one. However, in many SAR registration methods, the gradient calculation of the ASS is performed by using the simple differential equation which is not appropriate for SAR images. As the SAR images contain multiplicative speckle noise, simple difference operation is not suitable for gradient calculation. It can reduce the number of correct matches in SAR image registration. So, in this paper, a Gaussian-Gamma-Shaped Bi-Window (GGS-BW) is used for ratio based gradient computation which is very effective for SAR images. The proposed IAG-SIFT method significantly improves the matching performance between the SAR images. The Experimental results show the effectiveness of proposed IAGSIFT algorithm in SAR image registration.
Description: Copyright of this document belongs to proceedings publisher.
Appears in Collections:Conference Papers

Files in This Item:
File Description SizeFormat 
2017_INDICON_SPaul_SAR Image.pdfConference Paper431.93 kBAdobe PDFView/Open

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