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.

Icon Name Description
CloseImage E.g. removal of the "pepper" component of salt-and-pepper noise.
ConvolveImage Non-standard local transforms defined by the user.
DifferenceOfGaussians Emphasizes high-frequency image features such as lines or patches / dots.
DilateAndErodeImage Calculates dilation and erosion simultaneously for faster execution.
DilateImage Replaces each pixel with the maximum of pixels within a kernel.
DilateImage_AnyKernel Replaces each pixel with the maximum of pixels within an arbitrary kernel.
DilateImage_Mask Replaces each pixel with the maximum of pixels within a small rectangular kernel.
ErodeImage Replaces each pixel with the minimum of pixels within a kernel.
ErodeImage_AnyKernel Replaces each pixel with the minimum of pixels within an arbitrary kernel.
ErodeImage_Mask Replaces each pixel with the minimum of pixels within a small rectangular kernel.
GradientDirAndPresenceImage For highly optimized analysis of gradient directions.
GradientImage Computes a gradient image with smoothing operator of any size. The output pixels are signed.
GradientImage_Mask Computes a gradient image with a Sobel or Prewitt operator.
GradientMagnitudeImage Measures the strength of gradient at each pixel location with Sobel or Prewitt operator.
OpenImage E.g. removal of the "salt" component of salt-and-pepper noise.
SmoothImage_Deriche Approximation of the gaussian filter, which can be faster for large kernels.
SmoothImage_Gauss Removal of gaussian noise from images.
SmoothImage_Gauss_Mask Removal of gaussian noise from images (fast).
SmoothImage_Mean Usually used for computing features related to local image "windows". Can be also used for noise removal, but Gauss is superior here.
SmoothImage_Mean_AnyKernel Usually used for computing features related to local image "windows" having non-standard shape.
SmoothImage_Mean_Mask This is a faster alternative to SmoothImage_Mean when the kernel is very small.
SmoothImage_Median Edge-preserving noise removal (but slow).
SmoothImage_Median_Mask Replaces each pixel with the median of pixels within a 3x3 rectangular kernel (faster).
SmoothImage_Middle Useful for calculating per-pixel threshold values for image binarization.