Biomedical Image Segmentation: U-Net

Works with very few training images and yields more precise segmentation

Jingles (Hong Jing)
Towards Data Science
6 min readNov 7, 2019

--

Image Segmentation

Suppose we want to know where an object is located in the image and the shape of that object. We have to assign a label to every pixel in the image, such that pixels with the same label belongs to that object. Unlike object…

--

--

Alibaba PhD in machine learning | write about machine learning, neuroscience, healthcare & blockchain | reach me at linkedin.com/in/jingles