山东大学学报 (工学版) ›› 2022, Vol. 52 ›› Issue (3): 9-17.doi: 10.6040/j.issn.1672-3961.0.2021.319
• • 上一篇
郝晋一1,2,3,李鹏程1,2,3,黄艺美1,2,3,李金屏1,2,3*
HAO Jinyi1,2,3, LI Pengcheng1,2,3, HUANG Yimei1,2,3, LI Jinping1,2,3*
摘要: 针对X光机成像问题导致的轮胎顶部拉伸畸变图像,设计一种基于穿线预定位以及众数平滑提取特征的改进穿线法。分割胎侧区域,通过极值滤波消除水平帘线,利用垂直投影确定胎侧区域的粗边界;在胎侧区域进行预穿线确定最终穿线位置,并在选定位置利用众数平滑的方法提取线宽、线距等特征;根据提取的特征值计算线宽比、线距比以及均值、方差设计阈值进行畸变判断。在包含1000张正常图像与600张畸变图像的测试样本中进行试验,漏报率为2.3%,误报率为0%,相对于模板匹配等方法,检测结果更加准确检测、检测速率更快。
中图分类号:
[1] 邵明红. 轮胎缺陷检测的处理和算法研究[D]. 济南:山东大学控制科学与工程系, 2012. SHAO Minghong. Treatment and algorithm research of tires defects detection[D]. Jinan: Department of Control Science and Engineering, Shandong University, 2012. [2] 李杰. 基于轮胎质量检测成像与常见故障识别算法研究[D]. 沈阳:东北大学机械工程与自动化系, 2012. LI Jie. Research on the image of tyres quality test and common fault recognition algorithms[D]. Shenyang: Department of Mechanical Engineering and Automation, Northeastern University, 2012. [3] QI Xinwei, MIAO Ligang. A template matching method for multi-scale and rotated images using ring projection vector conversion[C] //Processdings of ICIVC 2018. Chongqing: IEEE, 2018. [4] ORON S, DEKEL T, XUE T, et al. Best-buddies similarity: robust template matching using mutual nearest neighbors[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(8): 1799-1813. [5] 王刚,施忠臣,尚洋,等. 结合模板匹配和梯度峰值的对角标志自动提取方法[J]. 光学学报, 2018, 38(8): 156-163. WANG Gang, SHI Zhongchen, SHANG Yang, et al. Automatic extraction of diagonal markers based on template matching and peaks of gradient histogram[J].Acta Optica Sinica, 2018, 38(8): 156-163. [6] 于向茹,丁健配,李金屏. 基于形态学与投影直方图的轮胎杂质缺陷检测[J]. 中国科学技术大学学报, 2019, 49(1): 49-54. YU Xiangru, DING Jianpei, LI Jinping. Tire impurity defect detection based on morphology and projection histogram[J]. Journal of University of Science and Technology of China, 2019, 49(1): 49-54. [7] ZHOU Zhihua, XIN Geng. Projection functions for eye detection[J]. Pattern Recognition, 2004, 37(5): 1049-1056. [8] GHOSH M, GUHA R, MONDAL R, et al. Feature selection using histogram-based multi-objective GA for handwritten devanagari numeral recognition[M]. Singapore: Springer, 2018: 471-479. [9] 郑修楠, 张潘杰, 李金屏. 基于穿线法的轮胎帘线弯曲缺陷检测[J]. 济南大学学报(自然科学版), 2018, 32(4): 286-290. ZHEN Xiunan, ZHANG Panjie, LI Jinping. Bending defect detection of tire cord based on threading method[J]. Journal of University of Jinan(Science and Technology), 2018, 32(4): 286-290. [10] LIU Ying, YAN Haoyang, LIM K P. Study on rotation-invariant texture feature extraction for tire pattern retrieval[J]. Multidimensional Systems and Signal Processing, 2017, 28(2): 757-770. [11] 卞国龙, 李勇, 戚顺青,等. 基于卷积神经网络的轮胎X射线图像缺陷检测[J]. 轮胎工业, 2019, 39(4): 247-251. BIAN Guolong, LI Yong, QI Shunqing, et al. Defect detection of tire by X ray image based on convolutional neural network[J]. Tire Industry, 2019, 39(4): 247-251. [12] ZHAO Guo, QIN Shiyin. High-precision detection of defects of tire texture through X-ray imaging based on local inverse difference moment features[J]. Sensors, 2018, 18(8): 2524. [13] WANG Ren, GUO Qiang, LU Shanmei, et al. Tire defect detection using fully convolutional network[J]. IEEE Access, 2019, 7: 43502-43510. [14] INDOLIA S, GOSWAMI A K, MISHRA S P, et al. Conceptual understanding of convolutional neural network-a deep learning approach[J]. Procedia Computer Science, 2018, 132: 679-688. [15] LIU Weibo, WANG Zidong, LIU Xiaohui, et al. A survey of deep neural network architectures and their applications[J]. Neurocomputing, 2017, 234: 11-26. [16] JI Zhong, SUN Yuxin, YU Yunlong, et al.Attribute-guided network for cross-modal zero-shot hashing[J]. IEEE Transactions on Neural Networks and Learning Systems, 2020, 31(1): 321-330. [17] REZATOFIGHI H, TSOI N, GWAK J Y, et al. Generalized intersection over union: a metric and a loss for bounding box regression[C] //Processdings of CVPR 2019. Long Beach, USA: IEEE, 2019: 658-666. [18] KONG T, SUN F, LIU H, et al. Foveabox: beyound anchor-based object detection[J]. IEEE Transactions on Image Processing, 2020, 29: 7389-7398. [19] REN S, HE K, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 39(6): 1137-1149. [20] CUI Xuehong, LIU Yun, ZHANG Yan, et al. Tire defects classification with multi-contrast convolutional neural networks[J]. International Journal of Pattern Recognition and Artificial Intelligence, 2018, 32(4): 18500. |
[1] | 董新宇,陈瀚阅,李家国,孟庆岩,邢世和,张黎明. 基于多方法融合的非监督彩色图像分割[J]. 山东大学学报 (工学版), 2019, 49(2): 96-101. |
[2] | 黄劲潮. 基于快速区域建议网络的图像多目标分割算法[J]. 山东大学学报(工学版), 2018, 48(4): 20-26. |
[3] | 李璐,范文涛,杜吉祥. 基于Markov随机场的Student's t混合模型的脑MR图像分割[J]. 山东大学学报(工学版), 2017, 47(3): 49-55. |
[4] | 胡金戈,唐雁. 基于视觉中心转移的视觉显著性检测方法[J]. 山东大学学报(工学版), 2017, 47(3): 27-33. |
[5] | 樊淑炎, 丁世飞. 基于多尺度的改进Graph cut算法[J]. 山东大学学报(工学版), 2016, 46(1): 28-33. |
[6] | 于海晶1,2, 李桂菊1*. 基于差分盒维数的彩色烟雾图像识别[J]. 山东大学学报(工学版), 2014, 44(1): 35-40. |
[7] | 戚世乐,王美清. 自适应分割弱边缘的活动轮廓模型[J]. 山东大学学报(工学版), 2013, 43(6): 17-20. |
[8] | 管燕,李存华*,仲兆满,孙兰兰. 化学分子结构图分割算法[J]. 山东大学学报(工学版), 2012, 42(5): 65-70. |
[9] | 张新明, 毛文涛, 李振云. 二阶广义概率的二维Otsu阈值分割[J]. 山东大学学报(工学版), 2012, 42(1): 25-33. |
[10] | 王丽娅, 潘振宽, 魏伟波*, 刘存良, 张志梅, 王钰. 多相图像分割的交替凸松弛优化及其Split Bregman算法[J]. 山东大学学报(工学版), 2011, 41(2): 40-45. |
[11] | 王新沛1,刘常春1*,白曈2. 基于均值距离的图像分割方法[J]. 山东大学学报(工学版), 2010, 40(4): 36-41. |
[12] | 冯显英 张成梁 杨丙生 李蕾. 基于RGB颜色空间的异性纤维识别检测算法[J]. 山东大学学报(工学版), 2009, 39(5): 68-72. |
[13] | 周广通,尹义龙,郭文鹃,任春晓. 基于协同训练的指纹图像分割算法[J]. 山东大学学报(工学版), 2009, 39(1): 22-26. |
[14] | 牛新生,叶华,王亮 . 彩色图像中的人脸检测方法[J]. 山东大学学报(工学版), 2007, 37(4): 0-0 . |
[15] | 马志强,常发亮,田伟,赵瑶 . 彩色图像中的人脸检测方法[J]. 山东大学学报(工学版), 2007, 37(4): 19-22 . |
|