This is meant to be a list of image processing techniques. Hopefully this list will be a valuable resource as one embarks on working on new image processing problem.
This is not a tutorial or explanation of any algorithms, and this is not going to give links to explanations or code. The point of this is to simply list all available options so that the programming/thinker can imagine possible algorithms to use to analyze the image.
- Filters
- Gaussian
- Laplacian
- Image morphology
- Erosion
- Dilation
- Image gradients
- Thresholding
- Adaptive thresholding
- Binary thresholding
- Otsu thresholding
- Segmentation
- Edge detection
- Canny edge detection
- Connected Components
- Haar Wavelets
- Contour detection
- Grayscale
- Histograms and histogram equalization
- Local equalization
- Gamma and log correction (see skimage.exposure)
- Hough transform
- Watershed algorithm
- Chroma-key algorithm
- Nonlocal means
- Sobel filter
- discrete fourier transform
- phase only transform
- Grabcut algorithm
- Gaussian Mixture Model (GMM)
- Check variance of pixels
- is infra-red/depth information available?
- Convex hull
- Medial Axis
- Corner Detection
- Daisy Feature Descriptor
- Frangi filter
- Censure feature detector
- Denoising
- Deconvolution
- Wiener algorithm and unsupervised Wiener algorithm
- Wavelets
- Region adjacency graphs
- Radon transform
Still to add: http://scikit-image.org/docs/dev/auto_examples/ segmentation of objects and below
- rag worth trying on vdos
- what is a wrapped image?
- plot_phase_unwrap.ipynb