纸病检测方法的研究进展

Advance in the test methods of paper defects

目前,纸病的检测技术研究主要集中于纸病的智能化在线检测,目的在于开发一套机器视觉系统,应用快速有效的算法,实现纸病的精确检测和定位。目前纸病检测方法分为阈值法、形态学方法、灰度级统计法三类。其中阈值法根据不同的纸病设置不同的阈值,形态学方法采用腐蚀和膨胀的边缘检测算子检测纸病边缘,灰度级统计法利用纸病图像的统计特征检测纸病。文章最后指出随着各种快速算法和高性能信号处理器件的出现,利用频域分析或是频域分析、统计方法和建模法的结合是纸病检测研究的一种趋势。

The research on paper defect detection technique is now focused on the intelligent on-line measurement, whose purpose is to develop a machine vision system to realize exact detection and localization of paper defects with a fast and effective algorithm. The test methods at present fall into three types： threshold method, morphological method and grey level statistics method. The threshold method sets up different threshold to different paper defects, morphological method detects the edge of paper defects with eroded and expanded edge detector and grey level statistics method detects paper defects with the statistical characteristics of the image of paper defects. It is pointed out that with emergence of various fast algorithm and high performance signal processors, the utilization of frequency domain analysis or the integration of the frequency domain analysis, statistical method and modeling method will be the trend for paper defect detect investigation.