Automatic SAR image enhancement based on nonsubsampled contourlet transform and memetic algorithm

Ying Li, Jie Hu, Yu Jia

Research output: Contribution to journalArticlepeer-review

26 Scopus citations

Abstract

This paper presents an automatic enhancement method for SAR images based on the nonsubsampled contourlet transform (NSCT) and the memetic algorithm (MA). Firstly, an improved enhancement function which integrates the speckle reduction with the feature enhancement is proposed to nonlinearly shrink and stretch the NSCT coefficients, and then an multi-population cooperative MA (MP-CMA) is presented to automatically adjust the parameters of the enhancement function. We propose an objective criterion for enhancement, and attempt finding the (near) optimal image according to the enhancement criterion. We employ the MP-CMA as a global search strategy for the best enhancement image which has a satisfactory compromise between sharpening and smoothing. The experimental results show that the proposed method can efficiently enhance the edge features and contrast of SAR images and reduce the speckle noises and outperforms the wavelet-based and NSCT-based non-automatic enhancement methods.

Original languageEnglish
Pages (from-to)70-78
Number of pages9
JournalNeurocomputing
Volume134
DOIs
StatePublished - 25 Jun 2014

Keywords

  • Image enhancement
  • Memetic algorithm
  • Nonsubsampled contourlet transform
  • SAR image
  • Speckle noise

Fingerprint

Dive into the research topics of 'Automatic SAR image enhancement based on nonsubsampled contourlet transform and memetic algorithm'. Together they form a unique fingerprint.

Cite this