Giter VIP home page Giter VIP logo

Comments (2)

PatRyg99 avatar PatRyg99 commented on July 17, 2024

For a binary mask EDT computes only distance for true pixels (with value of 1). Thus when calculating EDT only one time you get distance transform only for foreground mask (pixels with value of 0 stay as 0s). To calculate it for all pixels you need to invert the mask and run through EDT once more to obtain distance transform for background mask.

When you sum those two masks you create unsigned distance field and when subtract either one from the other you create signed distance field (one with negative and positive values). In paper authors describe that they used unsigned fields but I've run a couple tests and both unsigned and signed fields as well as one way transforms e.g. foreground and background, seem viable. This may depend on imbalance between the segmentation classes and segmentation shapes in particular problem.

from hausdorffloss.

abcxubu avatar abcxubu commented on July 17, 2024

I see. Thanks again for your reply.

from hausdorffloss.

Related Issues (6)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.