Title: Contourlet transform with modified particle swarm optimisation for despeckling and feature enhancement of SAR images
Authors: I. Shanthi; M.L. Valarmathi
Addresses: Sree Sakthi Engineering College, Karamadai, Coimbatore, Tamil Nadu, India ' Sree Sakthi Engineering College, Karamadai, Coimbatore, Tamil Nadu, India
Abstract: This paper gives a contourlet transform with modified PSO (MPSO) for the feature enhancement, edge preservation and despeckling of SAR images. In this paper, despeckling and preservation of edges are combined with improved gain function that optimises the contourlet coefficients for the enhancement of quality of denoised image. Furthermore, global search algorithm such as MPSO algorithm is applied for the best result. Increase in convergence speed and reduction in premature convergence are possible with MPSO that produces new learning scheme and a mutation operator. Contourlet transform with MPSO is compared with some of the standard speckle reduction filters and wavelet transform with MPSO. Experimental results show that the contourlet transform with MPSO gives better quality of image.
Keywords: SAR images; synthetic aperture radar; contourlet transform; MPSO; modified PSO; particle swarm optimisation; SAR despeckling; speckle suppression; adaptive despeckling; contourlet coefficients; PSNR; peak signal to noise ratio; SSI; speckle suppression index; SMPI; speckle suppression mean preservation index; image processing; image quality.
International Journal of Computer Applications in Technology, 2015 Vol.51 No.1, pp.31 - 42
Published online: 01 Apr 2015 *Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article