SpatialPack (version 0.3-8196)

denoise: Remove noise from an image

Description

This function removes noise from an input image.

Usage

denoise(img, type = "Lee", looks = 1, damping = 1)

Arguments

img

input grayscale image matrix.

type

character string, specifying the type of filter: "median", "Lee", "enhanced" (enhanced Lee filter), "Kuan" and "Nathan".

looks

specifies the equivalent (or effective) number of looks used to estimate noise variance, and it effectively controls the amount of smoothing applied to the image by the filter. A smaller value leads to more smoothing; a larger value preserves more distinct image features. The default value is looks = 1.

damping

specifies the extent of exponential damping effect on filtering, by default damping = 1.

Value

Filtered image, returned as a numeric matrix. It allows a better image interpretation. The denoise function clips output pixel values to the range \([0,1]\) after removing the noise.

Details

The median filter, in which each pixel is replaced by the median of nearby values is suitable to remove additive noise from an image.

The Lee filter reduces the speckle noise by applying a spatial filter to each pixel in an image, which filters the data based on local statistics calculated within a square window. The value of the center pixel is replaced by a value calculated using the neighboring pixels. Use the Lee filter to smooth speckled data that has a multiplicative component.

The Enhanced Lee filter is a refined version of the Lee filter, reducing the speckle noise effectively by preserving image sharpness and detail. Use the Enhanced Lee filter to reduce speckle while preserving texture information.

The Kuan filter follows a similar filtering process to the Lee filter in reducing speckle noise. This filter also applies a spatial filter to each pixel in an image, filtering the data based on local statistics of the centered pixel value that is calculated using the neighboring pixels.

Nathan filter is a particular case of the Kuan filter, obtained by puting looks = 1, and is thus applicable to 1-look SAR images only.

The size of the pixel window used to each filter is 3-by-3.

References

Lee, J.S. (1980). Digital image enhancement and noise filtering by use of local statistics. IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-2, 165-168.

Examples

# NOT RUN {
  data(texmos2)
  x <- imnoise(texmos2, type = "saltnpepper", epsilon = 0.10)
  plot(as.raster(x))

  y <- denoise(x, type = "median")
  plot(as.raster(y))

  x <- imnoise(texmos2, type = "speckle")
  plot(as.raster(x))

  y <- denoise(x, type = "Lee")
  plot(as.raster(y))
# }

Run the code above in your browser using DataCamp Workspace