基于网格的多目标模板匹配晶粒位置检测方法

周书辰; 陈晓荣; 王子旋

doi:10.3969/j.issn.1000-1158.2024.05.05

PDF(839 KB)

计量学报 ›› 2024, Vol. 45 ›› Issue (5) : 639-645. DOI: 10.3969/j.issn.1000-1158.2024.05.05

光学计量

基于网格的多目标模板匹配晶粒位置检测方法

周书辰,陈晓荣,王子旋

作者信息 +

Grid-based Multi-targets Template Matching Die Position Detection Method

ZHOU Shuchen,CHEN Xiaorong,WANG Zixuan

Author information +

文章历史 +

摘要

针对传统方法中晶粒位置检测的耗时长、精度低等局限性,提出一种基于网格的多目标模板匹配晶粒位置检测方法。通过改进传统的模板匹配方法,结合非极大值抑制算法,将芯片晶粒的检测速度和精度提高。实验结果表明:该算法在单一同种晶粒的算法识别率能够达到97%以上,单张图像耗时＜200ms,能够克服明暗不同造成的检测困难,达到技术指标要求。

Abstract

To address the limitations of traditional methods in terms of long detection time and low accuracy, a multi-objective template matching algorithm detecting position of die based on grid is proposed. By improving the traditional template matching method and combining with non-maximum suppression algorithm, the detection speed and accuracy of chip dice are improved. Experimental results show that the proposed algorithm has a recognition rate of over 97% for a single same die, and the single image processing time does not exceed 200ms. It can overcome the detection difficulties caused by different brightness and meet the technical specifications.

导出引用

周书辰,陈晓荣,王子旋. 基于网格的多目标模板匹配晶粒位置检测方法[J]. 计量学报. 2024, 45(5): 639-645 https://doi.org/10.3969/j.issn.1000-1158.2024.05.05

ZHOU Shuchen,CHEN Xiaorong,WANG Zixuan. Grid-based Multi-targets Template Matching Die Position Detection Method[J]. Acta Metrologica Sinica. 2024, 45(5): 639-645 https://doi.org/10.3969/j.issn.1000-1158.2024.05.05

中图分类号： TB96 TB973

参考文献

［1］于志斌, 胡泓. 基于YOLO算法与机器视觉的晶粒片表面缺陷检测研究［J］. 新型工业化, 2021, 11(12): 114-117.
YU Z B, HU H. Research on Surface Defect Detection of Grain Chips Based on YOLO Algorithm and Machine Vision［J］. The Journal of New Industrialization, 2021, 11(12): 114-117.
［2］陈治杉, 刘本永. 基于机器视觉的晶粒表面缺陷检测［J］. 贵州大学学报(自然科学版), 2019, 36(4): 68-73.
CHEN Z S, LIU B Y. Die surface defect detection based on machine vision［J］. Journal of Guizhou University, 2019, 36(4): 68-73.
［3］SAQLAIN M, ABBAS Q, LEE J Y. A deep convolutional neural network for wafer defect identification on an imbalanced dataset in semiconductor manufacturing processes［J］. IEEE Transactions on Semiconductor Manufacturing, 2020, 33(3): 436-444.
［4］周作梅, 李俊杰. 基于高斯滤波的低照度图像信息增强方法［J］. 信息与电脑(理论版), 2022, 34(17): 202-204.
ZHOU Z M, LI J J. A Low Illumination Image Information Enhancement Method Based on Gaussian Filter［J］. China Computer & Communication, 2022, 34(17): 202-204.
［5］周美丽, 白宗文. 基于Matlab的高斯模糊图像去噪方法研究［J］. 电子设计工程, 2014, 22(19): 167-168,172.
ZHOU M L, BAI Z W. Research on Gaussian Blur Image Denoising Method Based on Matlab［J］. International Electronic Elements, 2014, 22(19): 167-168,172.
［6］姒绍辉, 胡伏原, 顾亚军, 等. 一种基于不规则区域的高斯滤波去噪算法［J］. 计算机科学, 2014, 41(11): 313-316.
SI S H, HU F Y, GU Y J, et al. A Gaussian Filter Denoising Algorithm Based on Irregular Regions［J］. Computer Science, 2014, 41(11): 313-316.
［7］LIN H, DU P, ZHAO W, et al. Image registration based on corner detection and affine transformation［C］//2010 3rd International Congress on Image and Signal Processing. Yantai, China. 2010.
［8］DONG P, GALASANOS N P. Affine transformation resistant watermarking based on image normalization［C］//Proceedings International Conference on Image Processing. Rochester, USA. 2002.
［9］曾文锋, 李树山, 王江安. 基于仿射变换模型的图像配准中的平移、旋转和缩放［J］. 红外与激光工程, 2001(1): 18-20,17.
ZENG W F, LI S S, WANG J A. Translation, Rotation, and Scaling in Image Registration Based on Affine Transformation Model［J］. Infrared and Laser Engineering, 2001(1): 18-20,17.
［10］WEISSTEIN E W. Affine transformation ［EB/OL］. https: //mathworld. wolfram. com/, 2004.
［11］贾迪, 朱宁丹, 杨宁华, 等. 图像匹配方法研究综述［J］. 中国图象图形学报, 2019, 24(5): 677-699.
JIA D, ZHU N D, YANG N H, et al. Overview of Research on Image Matching Methods［J］. Journal of Image and Graphics , 2019, 24(5): 677-699.
［12］JIANG S P, XIANG W, LIU Y P, et al. Template matching using multi-feature co-occurrence matrix［J］. Optics and Precision Engineering, 2021, 29(6): 1459-1467.
［13］CHEN Z Y, LIU T, XIE J B, et al. Joint template matching algorithm for associated multi-object detection［J］. KSII Transactions on Internet and Information Systems, 2012, 6(1): 394.
［14］BRUNELLI R. Template matching techniques in computer vision: theory and practice［M］. New York:John Wiley & Sons, 2009.
［15］HASHEMI N S, AGHDAM R B, GHIASI A S B, et al. Template Matching Advances and Applications in Image Analysis［J］. American Scientific Research Journal for Engineering,Technology and Sciences (ASRJETS), 2016, 26(3): 91-108.
［16］WANG L T, LIU Q R. Discriminant distance template matching for image recognition［J］. Machine Vision and Applications, 2022, 33(6): 91.
［17］HAN Y. Reliable Template Matching for Image Detection in Vision Sensor Systems［J］. Sensors, 2021, 21(24): 8176.
［18］韩硕, 陈晓荣, 张彩霞, 等. 基于改进模板匹配算法的物料计数方法研究［J］. 计量学报, 2022, 43(7): 863-868.
HAN S, CHEN X R, ZHANG C X, et al. Research on Material Counting Method Based on Improved Template Matching Algorithm［J］. Acta Metrologica Sinica, 2022, 43(7): 863-868.
［19］侯志强, 刘晓义, 余旺盛, 等. 使用GIoU改进非极大值抑制的目标检测算法［J］. 电子学报, 2021, 49(4): 696-705.
HOU Z Q, LIU X Y, YU W S, et al. Using GIoU to Improve Non Maximum Suppression Target Detection Algorithm［J］. Chinese Journal of Electronics, 2021, 49(4): 696-705.
［20］BODLA N, SINGH B, CHELLAPPA R, et al. Soft-NMS-improving object detection with one line of code［C］//Proceedings of the IEEE international conference on computer vision. Venice, Italy, 2017.
［21］LIU S, HUANG D, WANG Y. Adaptive nms: Refining pedestrian detection in a crowd［C］//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. Long Beach, Los Angeles, USA, 2019.
［22］金柯, 陈晓荣. 基于机器视觉的光纤端面几何参数测量研究［J］. 计量学报, 2023, 44(2): 165-170.
JIN K, CHEN X R. Research on Measurement of Geometric Parameters of Optical Fiber Endface Based on Machine Vision［J］. Acta Metrologica Sinica, 2023, 44(2): 165-170.
［23］陈宗元, 张磊磊, 赵宁宁, 等. 混合颗粒系重叠图像分割与分类方法研究［J］. 计量学报, 2022, 43(6): 745-752.
CHEN Z Y, ZHANG L L, ZHAO N N, et al. Research on Segmentation and Classification Methods of Mixed Overlapped Particle Images［J］. Acta Metrologica Sinica, 2022, 43(6): 745-752.