yogeshhk/MidcurveNN
Computation of Midcurve of Thin Polygons using Neural Networks
This project helps engineers, designers, and manufacturing professionals automatically determine the "midcurve" of thin, closed 2D shapes like polygons. You provide the precise coordinates of a 2D closed polygon, and it outputs the coordinates for its central axis, which might be a single line or even branched. This is useful for tasks like tool path generation or structural analysis.
Use this if you need to precisely extract the central axis (midcurve) from 2D polygon designs for manufacturing, analysis, or design optimization.
Not ideal if your input shapes are highly complex 3D objects or if you need to process raster images directly without vectorizing them first.
Stars
42
Forks
17
Language
TeX
License
MIT
Category
Last pushed
Mar 26, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/yogeshhk/MidcurveNN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
daavoo/pyntcloud
pyntcloud is a Python library for working with 3D point clouds.
yangyanli/PointCNN
PointCNN: Convolution On X-Transformed Points (NeurIPS 2018)
torch-points3d/torch-points3d
Pytorch framework for doing deep learning on point clouds.
charlesq34/pointnet2
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
ranahanocka/MeshCNN
Convolutional Neural Network for 3D meshes in PyTorch