基于图像处理的金属机械零件表面微缺陷检测方法

Surface micro defect detection method of metal mechanical parts based on image processing

为了解决孔类金属零件内表面缺陷检测存在检测难度大、精度低等问题,提出一种基于图像处理的零件表面微缺陷检测方法。凭借CCD相机在孔类零件内部做回转运动与直线进给运动,获取完整的零件内表面图像;通过均值滤波均衡化目标缺陷灰度值,消除图片中的噪声,利用Canny算子提取缺陷边缘;利用腐蚀运算去除图像中结构元素较小的物体,使得边界点向内收缩,与膨胀运算相结合,完成孔洞的填充;将符合设定值的两个点连接在一起,得到完整的缺陷边缘图像;根据缺陷类型设定缺陷特征参数,完成缺陷类别的识别与检测。在仿真实验中,所提方法能够精准检测零件的微小缺陷,具有理想的检测效果。

In the inner surface defect detection of hole metal parts there are the problems of high detection difficulty and low accuracy.Based on this,a part surface micro defect detection method based on image processing is proposed.CCD camera is used to do rotary motion and linear feed motion in the hole parts to obtain a complete image of the inner surface of the parts.The gray value of the target defect is equalized by mean filtering to eliminate the noise in the picture,and the defect edge is extracted by Canny operator.The objects with small structural elements in the image are removed by corrosion operation so that the boundary points shrink inward,and the filling of holes is completed with the combination of expansion operation.The two points conforming to the set value are connected to obtain a complete defect edge image.The defect characteristic parameters are set according to the defect type to complete the identification and detection of the defect category.In the simulation experiment,the proposed method can accurately detect the small defects of parts and has an ideal detection effect.