2017 ◽  
Vol 25 (1) ◽  
pp. 188-197 ◽  
Author(s):  
屈玉福 QU Yu-fu ◽  
刘子悦 LIU Zi-yue ◽  
江云秋 JIANG Yun-qiu ◽  
周 丹 ZHOU Dan ◽  
王一帆 WANG Yi-fan

2013 ◽  
Vol 274 ◽  
pp. 667-670
Author(s):  
Yan Wei Wang ◽  
Si Qing Zhang ◽  
Bing Lin ◽  
Hong Liang ◽  
Yan Ming Pan

Feature Point Extraction Method of X-ray Image Based on Scale Invariant is proposed in this paper for industrial X-ray image with low contrast and some artifacts. First of all, the scale transformation of original image is adopted by the Gaussian kernel to building the DOG multi-scale pyramid. Then, the location and scale of the key points is fixed by the three-dimensional quadratic function. Finally, the Simply SIFT descriptor illustrates the key points. Experimental results show that the algorithm has good stability in translation, rotation and affine transformation, especially with 10 percent normalized Gaussian noise, this algorithm can still be detected feature points accuracy.


2011 ◽  
Vol 65 ◽  
pp. 407-410
Author(s):  
Xiao Qing Feng

Existing skeleton extraction methods, however, are often sensitive to noises and disconnected. This paper proposed a skeleton extraction method based on Poisson equation. It can approximate the topology structure of the input 3D model well, and avoid the broken lines. First, the proposed method extracts critical points of a 3D model by using Poisson equation and geodesic distance. Then the extracted critical points are connected and star skeleton of the 3D model is defined. Finally, the reverse force filed based Poisson energy distribution is used to push star skeleton into final result. Experiments show that the extracted skeleton is continuous and has no small branches affected model noises.


Sign in / Sign up

Export Citation Format

Share Document