Image denoising in contourlet domain based on a normal inverse Gaussian prior

“…Como solución ante distorsiones estructuradas, las más comunes en la adquisición de información visual de fenómenos reales, se han desarrollado métricas complementarias basadas en indicadores similares a los presentes en el sistema de visión humana, como es el caso del SSIM 8 , este es una función dependiente de la luminancia, el contraste y la similaridad estructural [32][33][34], tal como es expresado en (6) e ilustrado explícitamente en (7),…”

Section: Relación Señal-ruidounclassified

Obtención automática de siluetas a partir de imágenes adquiridas en condiciones de iluminación no controlada

S¹,

Archila²

2012

Iteckne

View full text Add to dashboard Cite

“…Synthetic aperture radar (SAR) images are extremely affected by speckle noise which causes error decisions about a target. We can refer to VISUShrink, 2 SUREShrink, 3 and BayesShrink 4 for the thresholding and generalized Gaussian mixture, 5 normal inverse Gaussian (NIG 6 ), and generalized Gamma distribution (GΓD) 7 for coefficient modeling. The best denoising method removes more speckle noise and has fewer blurring effects.…”

Section: Introductionmentioning

confidence: 99%

Two new methods based on contourlet transform for despeckling synthetic aperture radar images

Kiani

Ghofrani

2014

J. Appl. Remote Sens

View full text Add to dashboard Cite

We propose two methods for speckle suppression of synthetic aperture radar (SAR) images. The first method is based on Bayesian shrinkage and is a thresholding technique. The main problem of applying Bayesian shrinkage in a transformed domain, such as contourlet transform (CT), is finding the optimum threshold value. According to our experimental results, contourlet coefficients are affected by noise differently. It means that some contourlet coefficients belong to the specific sub-bands that are more robust against noise. We use this newfound property to determine the optimum threshold value and to develop our proposed method, which is named the weighted Bayesian shrinkage in contourlet domain. The second method, named the NSCT-GΓD, is a model-based approach using a two-sided generalized Gamma distribution (GΓD) to model the statistics of nonsubsampled contourlet transform (NSCT) coefficients. We use the Bayesian maximum a posteriori estimator to find NSCT despeckled coefficients. Experimental results carried out on both artificially speckled images and the true SAR images show that our two proposed methods outperform other approaches via two point of views, speckle noise reduction and image quality preservation.

show abstract

Image denoising in contourlet domain based on a normal inverse Gaussian prior

Cited by 26 publications

References 23 publications

Computer-aided obstructive sleep apnea detection using normal inverse Gaussian parameters and adaptive boosting

Computer-aided obstructive sleep apnea detection using normal inverse Gaussian parameters and adaptive boosting

Obtención automática de siluetas a partir de imágenes adquiridas en condiciones de iluminación no controlada

Two new methods based on contourlet transform for despeckling synthetic aperture radar images

Contact Info

Product

Resources

About