基于圆卷积神经网络的粘连导电粒子检测
Detection of conductive multi-particles based on circular convolutional neural network
刘子龙 1罗晨 1周怡君 1贾磊1
作者信息
- 1. 东南大学 机械工程学院,江苏 南京 211189;无锡尚实电子科技有限公司,江苏 无锡 214174
- 折叠
摘要
为了提高粘连导电粒子检测的精度和稳定性,提高评价指标的客观性和与实际生产需求的适配度,提出了基于圆卷积神经网络的粘连粒子检测.首先提出了更适合粒子检测的圆卷积,修改可变形卷积的采样策略,限制采样点偏移量x,y坐标的自由度,增加尺寸控制参数作为补偿.然后,基于U-MultiNet网络架构将圆卷积替代原有卷积形式,并增加注意力机制,通过标签图计算自注意力,以此作为权重修改损失函数和标签图.最后,提出可重复性和可再现性指标综合评价算法的精度和稳定性.实验结果表明,本文方法的可重复性和可再现性分别为0.809 2和0.705 1,相比现有主流方法提高了4.52%和1.74%;精确度和召回率分别为0.712 8和0.697 4,准确度为0.834 1,比现有主流方法高1.68%.相比于现有主流方法,该方法对于粘连干扰的粒子检测效果有明显提升,可以满足工业上对粒子检测精度、稳定性和实时性的要求.
Abstract
To enhance the accuracy and stability of conductive particle detection and to meet actual produc-tion demands,a multi-particle detection method based on a simplified deformable convolutional(circular convolutional)neural network is proposed.First,an appropriate model and network are chosen based on the characteristics of the detection task and target.Then,a deformable convolution sampling strategy is in-troduced and modified to restrict the sampling point offset,with added size control parameters.A circular convolution,more suitable for particle detection,replaces some convolutional layers of the original net-work.Additionally,an attention mechanism is introduced to calculate self-attention through label graphs,which serve as weight modification loss functions and label graphs.Finally,a comprehensive evaluation al-gorithm for the accuracy and stability of repeatability and reproducibility indicators is proposed.The results show that the repeatability and reproducibility indicators of our method are 0.809 2 and 0.705 1,respective-ly,outperforming existing mainstream methods by 4.52%and 1.74%.The accuracy and recall rates are 0.712 8 and 0.697 4,respectively,with an overall accuracy of 0.834 1,surpassing existing methods by 1.68%.Compared to existing mainstream methods,our approach significantly improves the particle detec-tion performance under adhesion interference,meeting industrial requirements for accuracy,stability,and real-time processing.
关键词
机器视觉/深度学习/神经网络/导电粒子检测/圆卷积Key words
machine vision/deep learning/neural network/conductive particle detection/circular convo-lution引用本文复制引用
基金项目
国家自然科学基金资助项目(51975119)
国家自然科学基金资助项目(52375487)
江苏省重点研发计划资助项目(BE2023041)
出版年
2024
国家科技期刊平台
NSTL
万方数据