网格布断裂缺陷检测方法的研究

针对传统自动化设备在网格布断裂缺陷检测方面的不足,提出了一种基于机器视觉的网格布断裂缺陷检测方法.首先,获取网格布的高对比度图像,利用中值滤波去掉图像中的噪声,采用Otsu阈值分割算法实现目标和背景的分离.根据网格部分断裂和完全断裂的两种缺陷特点,分别设计针对性算法.网格部分断裂的特点是由背景生成的凸包区域内包含有目标...

Research on the Mesh Fabric Fracture Defect Detection Method

Due to the deficiency of traditional automated equipment in the detection of mesh fabric fracture defects,a method based on machine vision for mesh fabric fracture defect detection is proposed.Firstly,the high-contrast image of the mesh fabric is obtained,the noise in the image is removed by median filtering,and the separation of object and background is achieved by Otsu threshold segmentation algorithm.According to the two defect characteristics of partial fracture and complete fracture in mesh,the corresponding algorithms are designed respectively.The characteristic of partial fracture in mesh fabric is that the convex hull region generated by the background contains the target object.Therefore,the combination of Blob analysis and convex hull detection is used to detect the defect.When the mesh is completely fractured,the location information of the defect region and the adjacent region will change.By analyzing the number of connected regions in circular region generated by the intersection of mesh skeleton,the identification of mesh complete fracture defects can be completed.The results show that the method can be applied to the detection of fracture defects in mesh.The recognition rate is more than 97%,which can meet the detection requirements.