Open AccessThree-Dimensional Reconstruction of Continuous Tomographic ICT Images of Defective SRM
Author(s) -
Ze Zhang,
Feng Gao,
Qian Zhang
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/816/1/012009
Subject(s) - computer science , artificial intelligence , computer vision , visualization , industrial computed tomography , segmentation , 3d reconstruction , enhanced data rates for gsm evolution , grayscale , noise reduction , tomographic reconstruction , iterative reconstruction , tomography , image (mathematics) , optics , physics
As an advanced technology for non-destructive testing of defective SRM, industrial computed tomography can visually show the structure of the SRM’s transverse section. 3D reconstruction of continuous tomographic images technology can convert the 2D images obtained into 3D visualization models, thus accurately determine the size and distribution of internal defects in the SRM, etc. Study the main technical methods of 3D reconstruction, it mainly includes 2D images denoising, edge detection and gray-scale image segmentation. Project, accumulate and render the pre-processed 2D images to obtain the 3D model, and then smooth the surface of the 3D model, the end result is a clear reconstruction model. The reconstructed 3D model can provide efficacious data support for SRM non-destructive testing, making the testing results more real and effective.