当前位置: X-MOL 学术Adv. Appl. Ceram. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Multi-scale decomposition enhancement algorithm for surface defect images of Si3N4 ceramic bearing balls based on stationary wavelet transform
Advances in Applied Ceramics ( IF 1.3 ) Pub Date : 2020-12-15 , DOI: 10.1080/17436753.2020.1858010
Dongling Yu 1 , Zuoxiang Zhu 1 , Jianliang Min 2 , Changfu Fang 1, 3 , Dahai Liao 1 , Nanxing Wu 1, 3
Affiliation  

ABSTRACT In order to improve the detection efficiency and image quality of Si3N4 ceramic bearing balls surface defects, digital image processing technology is used to analyse the information characteristics of Si3N4 ceramic bearing balls surface. A multi-scale decomposition enhancement algorithm for surface defect images of Si3N4 ceramic bearing balls based on the stationary wavelet transform is proposed. By building the surface defects detection system of Si3N4 ceramic bearing balls, the image enhancement program based on stationary wavelet transform with index low-pass filtering and nonlinear transform enhancement is designed. Finally, the effectiveness of the algorithm is verified by experiments. The experimental results show that the algorithm is applied to the surface defects image of Si3N4 ceramic bearing balls can effectively weaken the background noise and surface grinding texture, and enhance the contrast between defects and background clearly. In addition, the binary image is obtained by an adaptive threshold binary algorithm. After removing the tiny points by morphological opening operation, the defects are accurately and completely segmented, and then the Canny operator is used for edge detection to extract the edge contour of defects. When the decomposition level is set to 3, the average calculation time is 0.88 s, which are relatively short and have sufficient precision, and the algorithm can be extended to other kinds of ceramic ball surface damage detection.

中文翻译:

基于平稳小波变换的氮化硅陶瓷轴承球表面缺陷图像多尺度分解增强算法

摘要 为了提高Si3N4陶瓷轴承球表面缺陷的检测效率和图像质量,采用数字图像处理技术对Si3N4陶瓷轴承球表面信息特征进行分析。提出了一种基于平稳小波变换的氮化硅陶瓷轴承球表面缺陷图像多尺度分解增强算法。通过搭建Si3N4陶瓷轴承球表面缺陷检测系统,设计了基于平稳小波变换、指数低通滤波和非线性变换增强的图像增强程序。最后通过实验验证了算法的有效性。实验结果表明,将该算法应用于Si3N4陶瓷轴承球表面缺陷图像,可以有效减弱背景噪声和表面磨削纹理,明显增强缺陷与背景的对比。此外,二值图像是通过自适应阈值二值算法获得的。通过形态学开运算去除微小点后,对缺陷进行准确完整的分割,然后利用Canny算子进行边缘检测,提取缺陷的边缘轮廓。当分解级别设置为3时,平均计算时间为0.88 s,计算时间较短,精度足够,算法可以扩展到其他种类的陶瓷球表面损伤检测。并清晰地增强缺陷和背景之间的对比度。此外,二值图像是通过自适应阈值二值算法获得的。通过形态学开运算去除微小点后,对缺陷进行准确完整的分割,然后利用Canny算子进行边缘检测,提取缺陷的边缘轮廓。当分解级别设置为3时,平均计算时间为0.88 s,相对较短且精度足够,算法可以扩展到其他类型的陶瓷球表面损伤检测。并清晰地增强缺陷和背景之间的对比度。此外,二值图像是通过自适应阈值二值算法获得的。通过形态学开运算去除微小点后,对缺陷进行准确完整的分割,然后利用Canny算子进行边缘检测,提取缺陷的边缘轮廓。当分解级别设置为3时,平均计算时间为0.88 s,相对较短且精度足够,算法可以扩展到其他类型的陶瓷球表面损伤检测。然后使用 Canny 算子进行边缘检测,提取缺陷的边缘轮廓。当分解级别设置为3时,平均计算时间为0.88 s,相对较短且精度足够,算法可以扩展到其他类型的陶瓷球表面损伤检测。然后使用 Canny 算子进行边缘检测,提取缺陷的边缘轮廓。当分解级别设置为3时,平均计算时间为0.88 s,相对较短且精度足够,算法可以扩展到其他类型的陶瓷球表面损伤检测。
更新日期:2020-12-15
down
wechat
bug