聚晶金刚石复合片表面裂纹视觉检测技术研究

采用计算机视觉检测技术提取出表面缺陷特征量,完成聚晶金刚石复合片表面裂纹缺陷检测。首先,根据聚晶金刚石复合片表面特性,研究合适的光源照明系统。然后,提出一种基于直方图投影梯度极值的局部边界提取方法,将感兴趣区域进行提取。在此基础上,采用图像滤波、阈值分割的方法实现裂纹的准确提取。最后,通过计算裂纹连通域的圆形度和长宽比进行裂纹识别。实验结果表明,本方法可有效地对聚晶金刚石复合片表面裂纹缺陷进行检测。

Vision Detection Technology Research for Surface Crack of Polycrystalline Diamond Compact

Computer vision detection technology was adopted to extract the defect feature quantity of the surface, and further completed the detection of surface crack defects in polycrystalline diamond compact. First, according to the features of polycrystalline diamond compact, the appropriate light source lighting system was studied. Then, a local boundary extraction method based on the histogram projection gradient extremum was proposed, and the region of interest (ROI) was extracted. On this basis, the method of image filtering and threshold segmentation were used to realize the accurate extraction of the crack. Finally, the crack was identified by calculating the circularity factor and aspect ratio of the cracked domain. Experimental results showed that this method can effectively detect the surface crack defects of polycrystalline diamond compact.