Primarily this library was developed for producing a set of super-pixels from an image (i.e. an over-segmentation). The segmentation is produced by running multiple instances of Dijkstra's Algorithm from a set of seed points; those nodes which belong to a given Dijkstra cloud form a segment (so the number of segments is fixed and determined at the beginning of the algorithm). The goal is to add code that moves from the over-segmentation to a more useful segmentation. The library includes code specifically for the purpose of image segmentation but there are several components useful for general graph segmentation.
License
BSD LicenseFollow graphseg
nel_h2
Simply solve complex auth. Easy for devs to set up. Easy for non-devs to use.
Custom auth drains 25% of dev time and risks 62% more breaches, stalling enterprise deals. Frontegg platform delivers a simple login box, seamless authentication (SSO, MFA, passwordless), robust multi-tenancy, and a customizable Admin Portal. Integrate fast with the React SDK, meet compliance needs, and focus on innovation.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of graphseg!