Back to Adaptive Vision Studio website

You are here: Start » Filter Reference » Image Local Transforms

Image Local Transforms

Select a filter from the list below.

IconNameDescription
CloseImageE.g. removal of the "pepper" component of salt-and-pepper noise.
ConvolveImageNon-standard local transforms defined by the user.
DifferenceOfGaussiansEmphasizes high-frequency image features such as lines or patches / dots.
DilateAndErodeImageCalculates dilation and erosion simultaneously for faster execution.
DilateImageReplaces each pixel with the maximum of pixels within a kernel.
DilateImage_AnyKernelReplaces each pixel with the maximum of pixels within an arbitrary kernel.
DilateImage_MaskReplaces each pixel with the maximum of pixels within a small rectangular kernel.
ErodeImageReplaces each pixel with the minimum of pixels within a kernel.
ErodeImage_AnyKernelReplaces each pixel with the minimum of pixels within an arbitrary kernel.
ErodeImage_MaskReplaces each pixel with the minimum of pixels within a small rectangular kernel.
GradientDirAndPresenceImageFor highly optimized analysis of gradient directions.
GradientImageComputes a gradient image with smoothing operator of any size. The output pixels are signed.
GradientImage_MaskComputes a gradient image with a Sobel or Prewitt operator.
GradientMagnitudeImageMeasures the strength of gradient at each pixel location with Sobel or Prewitt operator.
OpenImageE.g. removal of the "salt" component of salt-and-pepper noise.
SmoothImage_DericheApproximation of the gaussian filter, which can be faster for large kernels.
SmoothImage_GaussRemoval of gaussian noise from images.
SmoothImage_Gauss_MaskRemoval of gaussian noise from images (fast).
SmoothImage_MeanUsually used for computing features related to local image "windows". Can be also used for noise removal, but Gauss is superior here.
SmoothImage_Mean_AnyKernelUsually used for computing features related to local image "windows" having non-standard shape.
SmoothImage_Mean_MaskThis is a faster alternative to SmoothImage_Mean when the kernel is very small.
SmoothImage_MedianEdge-preserving noise removal (but slow).
SmoothImage_Median_MaskReplaces each pixel with the median of pixels within a 3x3 rectangular kernel (faster).
SmoothImage_MiddleUseful for calculating per-pixel threshold values for image binarization.