"A Generalization of Otsu's Method and Minimum Error Thresholding", Jonathan T. Barron, ECCV 2020
Ғылым және технология
paper: arxiv.org/abs/2007.07350
code: github.com/jonbarron/hist_thresh
More at jonbarron.info/
Errata: When describing Otsu's method, I say "k-means in 2D" when I should have said "k-means in 1D".
Пікірлер: 4
When you study statistics and probability before training a NN on 10 million images! Thank you for such a straightforward explanation.
Impressive! Great job at explaining everything so clearly! It was delightful to learn about this topic! Thank you! 🤓
Great work! I saw your tweet and found it funny. This work makes me thinks there is a lot more to be done with traditional (non neural) algorithms
Brilliant work