JasonGellis
commented
3 years ago Adaptive thresholding methods are those that do not use the same threshold throughout the whole image. This may be applicable for thresholding issues we are facing with lithic features (e.g. rifges vs. ripples).
- Note: thresholding works best with grayscale.
Sci-Kit Adaptive thresholding check that documentation matches package as thresholding names may have changed If there’s large variation in the background intensity, however, adaptive thresholding (a.k.a. local or dynamic thresholding) may produce better results. https://scikit-image.org/docs/stable/auto_examples/applications/plot_thresholding.html
OpenCV Image Thresholding (includes algo for adapative thresholding) Uses Otsu's binarization, which assumes the image contains two classes of pixels - foreground and background, and has a bi-modal histogram. It then attempts to minimize their combined spread (intra-class variance) to automatically determine thresholding vaues. https://docs.opencv.org/3.4/d7/d4d/tutorial_py_thresholding.html
Image bluring, post process for thresholding https://medium.com/spinor/a-straightforward-introduction-to-image-thresholding-using-python-f1c085f02d5e
Explore medical imaging applications of trainable thresholding for lithic images.