opencv_filter_2d · Custom convolution
2D convolution with any kernel you write down as a numeric matrix.
2D convolution with any kernel you write down as a numeric matrix.
Directional texture filtering with Gabor kernels — a classic for fingerprint/fabric analysis.
Gaussian-weighted blur: natural smoothing, the default choice for denoising.
Reads one image from disk (png / jpg / bmp / tiff / webp …) as the graph’s input source.
Writes the upstream image to a file; the format is inferred from the extension.
Second-derivative operator: isotropic edge/texture response, used for sharpening and edge detection.
Median filter: takes the median in the window — extremely effective on salt-and-pepper noise, edge-preserving.
Open/close/gradient/top-hat/black-hat: the composed morphology operations in one node.
Gaussian blur + halved size: anti-aliased downsampling.
Upscale ×2 then blur: the pyramid inverse.