锻压技术

基于双阈值图像区域生长法的冲压件划痕检测

英文标题：Scratch detection on stamping part based on double threshold image region growth method

作者：田洪志王东兴林建钢陈麒麟

单位：烟台大学

分类号：TP391

出版年,卷(期):页码：2020,45(6):175-181

摘要：

当冲压件划痕缺陷区域的灰度值与背景的灰度值差异不大时，使用传统的图像分割方法易出现噪声较多或划痕特征无法提取的情况。为此，提出了一种基于动态阈值分割的双阈值图像区域生长法。首先，对采集的冲压件图像进行两次不同阈值的动态阈值分割，得到两个不同阈值的二值图像；其次，结合两个不同阈值的二值图像使用区域生长法得到优化二值图像；最后，对生长完成后的优化二值图像通过面积和结构因子特征参数进行区域筛选，提取划痕缺陷。实验结果表明，使用本方法检测冲压件划痕缺陷，能够满足工厂检测要求，具有检测效率高、准确性高的优点。

When the gray value of scratched defect area for stamping part has little difference with that of background, the traditional image segmentation method is prone to producing too much noise or the situation that the scratch features cannot be extracted. Therefore, the double threshold image region growth method based on dynamic threshold segmentation was proposed. Firstly, the collected images of stamping part were segmented by dynamic threshold with two different thresholds, and binary images with two different thresholds were obtained. Then, the optimized binary images were dstained by region growth method combining binary images with two different thresholds. Finally, the optimized binary image after the growth was screened by area and structure factor characteristic parameters to extract the scratch defects. The experimental results show that using this method to detect the scratch defects of stamping parts meets the requirements of factory inspection and has the advantages of high detection efficiency and high accuracy.

基金项目：

国家自然科学基金青年项目(11604285)

田洪志(1994-)，男，硕士研究生 E-mail：1017694473@qq.com 通讯作者：王东兴(1964-)，男，博士，教授 E-mail：dxwang@ytu.edu.cn

参考文献：

［1］王庆阳,高梦迪,李磊,等.冲压成形节能优化方法
［J］.锻压技术,2019,44(6):134-144.

Wang Q Y，Gao M D，Li L，et al. Energy-saving optimization method of stamping
［J］. Forging & Stamping Technology，2019，44（6)：134-144.

［2］汤勃,孔建益,伍世虔.机器视觉表面缺陷检测综述
［J］.中国图象图形学报,2017,22(12):1640-1663.

Tang B，Kong J Y，Wu S Q. Review of surface defect detection based on machine vision
［J］. Journal of Image and Graphics，2017，22（12）: 1640-1663.

［3］李克斌,余厚云,周申江.基于形态学特征的机械零件表面划痕检测
［J］.光学学报,2018,38(8):260-266.

Li K B，Yu H Y，Zhou S J. Surface scratch detection of mechanical parts based on morphological features
［J］. Acta Optica Sinica，2018，38（8）：260-266.

［4］李晨,杨甬英,熊浩亮,等.基于滤波差分的双阈值弱划痕提取算法
［J］.强激光与粒子束,2015,27(7):97-104.

Li C，Yang Y Y，Xiong H L，et al.Dual-threshold algorithm study of weak-scratch extraction based on the filter and difference
［J］. High Power Laser and Particle Beams，2015，27（7）：97-104.

［5］赵文宏,彭超,陈红星.基于形态学玻璃屏幕表面划痕检测方法研究
［J］.浙江工业大学学报,2016,44(3):279-282.

Zhao W H，Peng C，Chen H X. Study on scratch inspection methods of glass screen surface based on morphology
［J］. Journal of Zhejiang University of Technology，2016，44(3)：279-282.

［6］Hu K, Zhang S Y, Xu J H. Scratch detection technology for product surface based on improved contourlet transform
［J］. IOP Conference Series: Materials Science and Engineering,2017, 242: 23-25.

［7］李家宏,陈斌.基于k-邻域前景像素分析的划痕提取方法
［J］.计算机应用,2017,37(S2):175-178.

Li J H，Chen B. Scratches extraction method based on analysis of foreground pixel of k-adjacent domain
［J］. Journal of Computer Applications，2017，37（S2）：175-178.

［8］张杰,张末含,邢海花,等.基于图像处理的橡胶树割痕提取与死皮识别
［J］.计算机应用与软件,2019, 36(1):259-262，329.

Zhang J，Zhang M H，Xing H H，et al. Extraction of cut marks and identification of TPD of rubber tree based on image processing
［J］. Computer Applications and Software，2019，36（1）：259-262，329.

［9］毛星云.OpenCV3编程入门
［M］.北京：电子工业出版社，2015.

Mao X Y. OpenCV3 Programming Entry
［M］.Beijing：Publishing House of Electronics Industry，2015.

［10］徐信.冲压件表面缺陷图像检测系统的研究与开发
［D］.广州:广东工业大学,2016.

Xu X. Study and Development of Surface Defect Detecting System of Stamping Parts Based on Image Processing
［D］. Guangzhou: Guangdong University of Technology，2016.

［11］张俊生,王明泉,郭晋秦,等. BGA焊点气泡缺陷X射线图像的动态阈值分割方法
［J］.火力与指挥控制, 2018,43(10):113-116.

Zhang J S，Wang M Q，Guo J Q，et al. Dynamic threshold segmentation of bubble defects in BGA solder balls
［J］. Fire Control & Command Control，2018，43（10）：113-116.

［12］李小磊,曾曙光,郑胜,等. 基于滑动滤波和自动区域生长的陶瓷瓦表面裂纹检测方法
［J］.激光与光电子学进展,2019,56(21):49-56.

Li X L，Zeng S G，Zheng S，et al. Surface crack detection of ceramic tile based on sliding filter and automatic region growth
［J］. Laser & Optoelectronics Progress，2019，56（21）：49-56.

服务与反馈：

【文章下载】【加入收藏】