计算机工程
計算機工程
계산궤공정
COMPUTER ENGINEERING
2009年
23期
222-223,226
,共3页
偏微分方程%图像平滑%疵病
偏微分方程%圖像平滑%疵病
편미분방정%도상평활%자병
Partial Differential Equations(PDE)%image smoothing%defects
传统的图像平滑方法在去除噪声的同时往往会破坏边缘、线务、纹理等图像特征,而基于偏微分方程(PDE)的各向异性扩散算法在抑制噪声的同时能够保持这些特征.研究基于PDE的图像去噪平滑算法并对PDE算法的不足作出改进,将其用于图像去噪处理效果非常理想,并在精密光学元件表面疵病识别的实验中取得较好的效果.
傳統的圖像平滑方法在去除譟聲的同時往往會破壞邊緣、線務、紋理等圖像特徵,而基于偏微分方程(PDE)的各嚮異性擴散算法在抑製譟聲的同時能夠保持這些特徵.研究基于PDE的圖像去譟平滑算法併對PDE算法的不足作齣改進,將其用于圖像去譟處理效果非常理想,併在精密光學元件錶麵疵病識彆的實驗中取得較好的效果.
전통적도상평활방법재거제조성적동시왕왕회파배변연、선무、문리등도상특정,이기우편미분방정(PDE)적각향이성확산산법재억제조성적동시능구보지저사특정.연구기우PDE적도상거조평활산법병대PDE산법적불족작출개진,장기용우도상거조처리효과비상이상,병재정밀광학원건표면자병식별적실험중취득교호적효과.
The conventional image smoothing methods can eliminate noise as well as smear the image features such as edges, lines and textures, while the anisotropic diffusion algorithm based on Partial Differential Equations(PDE) not only can suppress the noise but also can preserve these features. This paper studies noise smoothing algorithm based on PDE and improves its insufficiency, and the result is very satisfactory by using the algorithm, and is satisfyingly in the precision optics part surface defect recognition experiment.