基于多区域变形补偿的印刷文字缺陷检测算法研究

Research on defect detection algorithm of printed text based on multi-region deformation compensation

针对塑料薄膜印刷品由于产品变形、字符窄小、背景复杂等因素导致文字缺陷不易检测的难点问题,在HALCON图像处理软件平台上,提出了图像分区域检测、多区域变形补偿和训练差分模型的改进算法.在变形补偿的基础上通过待检测图像与差分模型的比对,得到塑料薄膜印刷品的文字缺陷信息.实验表明,该算法检测缺陷正确率高,检测出的文字缺陷与实际产品缺陷吻合度高,能满足包装产品批量化生产的要求,且该算法具有快速性和高效性.

For the difficult problems of detecting the character defects of plastic film printing caused by the distortion of the product,the narrow character,the complicated background and other factors.An improved algorithm including image subarea detection,multi-region deformation compensation and training difference model is proposed on the HALCON image processing software platform in this paper.By comparing the image to be detected with the difference model,plastic film printing character defects information is obtained on the basis of the deformation compensation.The experiment results show that the algorithm has the advantages of high detection accuracy,high degree of consistency between the detected defects and the actual defects,and can meet the requirements of mass production of packaging products.And the algorithm is fast and efficient.