基于机器视觉的植球缺陷识别技术  

Ball planting defect identification technology based on machine vision

作　　者：吴乐福 WU Lefu(School of Mechanical Engineering,University of Shanghai for Science and Technology,Shanghai 200093,China)

机构地区：[1]上海理工大学机械工程学院,上海200093

出　　处：《农业装备与车辆工程》2024年第10期119-123,共5页Agricultural Equipment & Vehicle Engineering

摘　　要：植球缺陷是芯片制造过程中常见的问题之一,如果不及时检测和修复,可能会导致芯片性能下降或故障。基于机器视觉技术,研究并设计了一种用于芯片植球缺陷检测的方法,旨在提高芯片制造过程中的质量控制能力。通过收集大量包含正常与缺陷样本的芯片植球图像数据集,运用计算机视觉算法进行深入处理与分析。研究过程中,对图像进行了预处理,例如去噪和图像增强,以提升缺陷检测的准确性。进一步采用图像分割算法,有效地将芯片植球从图像背景中分离,便于精确检测缺陷。此外,利用特征提取算法识别芯片植球的独特性质,并通过分类算法准确区分正常与缺陷芯片样本。不仅提高了芯片缺陷检测的精准度,而且为工业生产中的质量控制提供了重要依据,具有积极的现实意义。Ball planting defects are one of the common problems in the chip manufacturing process,which may lead to chip performance degradation or failure if not detected and repaired in time.Utilizing machine vision technology,designs and studies a technique for detecting chip seeding defects with the aim of enhancing quality control in the chip fabrication process.By assembling a comprehensive dataset of chip balling images,both normal and defective,and employing advanced computer vision algorithms for in-depth processing and analysis,the study undertakes a rigorous examination.During this process,image preprocessing techniques such as denoising and enhancement were utilized to improve the accuracy of defect detection.Further,image segmentation algorithms were applied to effectively isolate chip balling from the background,facilitating precise defect identification.Additionally,feature extraction algorithms were employed to identify the distinctive characteristics of chip balling,and classification algorithms were used to accurately differentiate between normal and defective chip samples.Not only does it improve the accuracy of chip defect detection,but it also provides important basis for quality control in industrial production,which has positive practical significance.

关 键 词：机器视觉 芯片植球 缺陷检测 图像处理 特征提取 分类算法 

分 类 号：TN40[电子电信—微电子学与固体电子学] TP391.41[自动化与计算机技术—计算机应用技术]