Method for extracting multi-dimension curvature characteristic on triangle gridding
A triangular grid and feature extraction technology, applied in image data processing, measurement devices, 3D modeling, etc., can solve problems such as unsatisfactory feature extraction, insufficient model understanding, and no clear division of detailed features and coarse-grained features.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0025] refer to figure 1 , represents the flow chart of the extraction method of the present invention. The input data is a triangular mesh of arbitrary topology to be analyzed. The present invention first adopts the method of adjacent principal component analysis, a multi-scale grid curvature information estimation, a1 uses spherical function and its derivative function and grid characteristic function to do convolution; a2 obtains the principal component through principal component analysis and reverses Find the principal curvature; a3 calculate the Gaussian curvature information based on the multi-scale principal curvature; b construct a grid feature descriptor set that satisfies the local quadratic surface constraint through the constraint form of the Gaussian curvature on the quadric surface, and b1 divide the grid vertices according to The Gaussian curvature is sorted from large to small; b2 constructs a local frame according to its curvature direction and normal direct...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 