摘要
该文结合氟塑料薄膜生产特点提出采用多线阵CCD并行采集数据,并配合选择性像素级图像融合算法、粗—细检测两步策略的图像处理算法的在线检测方法。在选择性图像融合算法中,若各CCD采集的图像均不含疵点,则不进行融合;只要有一帧数据含有疵点,就进行融合。由于待检测薄膜表面大部分区域没有疵点,故采用粗—细检测两步策略的图像处理算法。实验表明该方法是一种实用有效的疵点检测方法,可满足氟塑料薄膜在线检测要求。
According to the fluoride plastic film production features,this article presents an online inspection scheme which uses multi-linear CCD to collect data in parallel,coordinating with selective pixel level image fusion algorithm,two-step strategy of rough detection and fine detection.In the selective pixel level image fusion algorithm,if there are no defects in the image,the image fusion will not be done.There are no defects in most areas,so this article chooses two-step strategy of rough detection and fine detection.The test result shows that it is a practical and fit defects inspection scheme, which can meet the need of fluorine plastic film on-line inspection.
出处
《微型电脑应用》
2009年第4期48-50,6,共3页
Microcomputer Applications
基金
国家自然科学基金重点项目(60534020)
国家自然科学基金(60775052)
教育部科技创新工程重大项目培育资金项目(706024)
上海市国际科技合作基金项目(061307041)
关键词
多线阵CCD
图像融合
图像处理
疵点检测
在线检测
Multi-linear CCD
Image fusion
Image processing
Defects inspection
On-line inspection
