基于灰度共生矩阵的注塑模具瑕疵检测  

The detection of residuum in injection mold based on gray level co-occurrence matrix

作　　者：马琳[1] 王直杰[1] 朱晓明[1] 许骏[1] 

机构地区：[1]东华大学,上海201620

出　　处：《电子设计工程》2015年第7期138-140,144,共4页Electronic Design Engineering

基　　金：国家自然科学基金资助(61075105)

摘　　要：遗留物检测是注塑机工作过程中的一项重要工作。为实现比较精确的模具遗留物检测,在对图像进行位置偏差矫正等预处理之后利用灰度共生矩阵算法,对标准图像与采集图像进行纹理分析,得到了这两幅注塑模具图像的特征参数,取四个特征参数进行分析,利用加权欧式距离对两组参数进行相似度比较,从而判断采集的图像是否为瑕疵图像。最后,利用OPENCV图像处理技术对系统进行了实现,并且和常用方法差影法进行了比较,试验结果表明,在光照不稳定情况下,提出的算法在注塑模具的遗留物检测中适用性更强。Detection of residuum is very important in the working process of the injection molding machine.In order to achieve ideal result of detection, this paper gets the characteristic parameters by analyzing the texture of standard picture and defective picture with gray level co-occurrence matrix algorithm after making some corresponding pretreatment to them including deviation correction of their positons. This paper mainly uses four characteristic parameters, then use Weighted Euclidean distance to compare their similarity to judge whether the tested picture is defective. At last, this paper uses the image processing technology based on OpenCV [1] to detect the residuum, and compares this algorithm with common algorithm. The result indicates that the algorithm of this paper is superior in the area of the detection of residuum in the ease of unstable light conditions.

关 键 词：图像处理 遗留物 灰度共生矩阵 OPENCV 注塑模具 

分 类 号：TN06[电子电信—物理电子学]