摘要
定量金相是金相学发展的一个重要方向,球化珠光体的检测是珠光体球化评级的先决条件。该文研究了如何利用数字图像处理技术检测金相图像中的球化珠光体。提出了用可变模板匹配的方法来检测球化珠光体,针对珠光体的形态的不同,设计了两种可变模板。然后,用人工神经网络的方法来认别出球化珠光体。实验表明本方法有较好的效果。
Quantitative metallography is a important development of metallography.Spherular pearlite detection is a required preliminary step to gradational of spherular pearlite.In this paper,a research on spherular pearlite detection using digital image processing technic is worked.A method which employ deformable template matching is proposed to detect spherular pearlite.Two deformable template is de-signed for two form spherular pearlite respectively.Then,artificial neural network is employed to recognise spherular pearlite.Experimental results shows the effectiveness of this method.
出处
《电脑知识与技术(过刊)》
2009年第3X期2026-2028,共3页
Computer Knowledge and Technology
关键词
数字图像处理
可变模板匹配
球化珠光体检测
digital image process
deformable template match
spherular pearlite detection