引用本文:
【打印本页】   【下载PDF全文】   查看/发表评论  【EndNote】   【RefMan】   【BibTex】
←前一篇|后一篇→ 过刊浏览    高级检索
本文已被:浏览 216次   下载 61 本文二维码信息
码上扫一扫!
分享到: 微信 更多
基于改进Faster R-CNN的零食包装盒表面缺陷检测
巩雪1,孙雪刚1,褚洋洋2,崔功卓1,李欣妍1
1.哈尔滨商业大学 轻工学院,哈尔滨 150028;2.黑龙江林业职业技术学院 生态工程系,黑龙江 牡丹江 157011
摘要:
目的 针对现有食品包装盒表面缺陷检测方法存在的复杂背景下小目标缺陷检测难、漏检率高、检测精度低等问题,选择生活中常见的绿豆糕零食包装盒作为检测对象,提出一种基于改进Faster R-CNN的绿豆糕包装盒表面缺陷检测方法。方法 以Faster R-CNN算法架构为基础,以Swin Transformer V2-T为特征提取主干,初步提高算法对包装盒缺陷特征的提取能力;结合加权双向特征金字塔网络(Bidirectional Feature Pyramid Network,BiFPN)自适应调节每个尺度特征图的权重并对不同尺寸的特征进行多尺度融合,以提高识别的准确率;通过ROIAlign结合ECA注意力机制替换ROIPooling,去除2次量化误差并进一步优化算法对包装盒缺陷的检测能力。结果 本检测方法可准确提取目标缺陷,绿豆糕包装盒表面的4种缺陷的检测平均精确率(Average Precision,AP)较改进前分别提高19.66、12.96、14.56、18.86百分点,同时平均精确率均值(mean Average Precision,mAP)在IoU为0.5上较改进前提高了15.76百分点。结论 改进后的模型为Faster R-CNN在食品包装盒智能化生产上的应用了提供有益的参考和经验。
关键词:  零食包装盒  缺陷检测  Faster R-CNN  加权双向特征金字塔网络(BiFPN)  Swin TransformerV2
DOI:10.19554/j.cnki.1001-3563.2024.23.025
分类号:
基金项目:黑龙江省属高等学校基本科研业务费项目(2023-KYYWF-1011)
Surface Defect Detection of Snack Packaging Box Based on Improved Faster R-CNN
GONG Xue1, SUN Xuegang1, CHU Yangyang2, CUI Gongzhuo1, LI Xinyan1
(1. School of Light Industry, Harbin University of Commerce, Harbin 150028, China;2. Department of Ecological Engineering, Heilongjiang Forestry Vocational and Technical College, Heilongjiang Mudanjiang 157011, China)
Abstract:
Aiming at the problems that the existing food packaging box surface defect detection methods have difficulty in small target defect detection under complex background, high missed detection rate and low detection accuracy, with the mung bean cake snack packaging box common in life as the detection object, the work aims to propose a mung bean cake packaging box surface defect detection method based on improved Faster R-CNN. Firstly, based on the Faster R-CNN algorithm architecture, Swin Transformer V2-T was used as the feature extraction backbone to preliminarily improve the ability of the algorithm to extract the features of the packaging box defect. Secondly, combined with the weighted bidirectional feature Pyramid Network (BiFPN), the weight of each scale feature map was adjusted and the multi-scale fusion was conducted on features of different sizes to improve the recognition accuracy. Finally, ROIAlign was combined with the ECA attention mechanism to replace ROIPooling, removing two quantization errors and further optimizing the detection ability of the algorithm for packaging box defects. The detection method proposed could accurately extract the target defects, and the Average Precision (AP) of the four defects on the surface of the mung bean cake packaging box increased by 19.66%, 12.96%, 14.56%, and 18.86% respectively. At the same time, the mean average precision (mAP) increased by 15.76% when the IOU was 0.5. The improved model provides useful reference and experience for the application of Faster R-CNN in the intelligent production of food packaging boxes.
Key words:  snack packaging box  surface defect detection  Faster R-CNN  Bidirectional Feature Pyramid Network (BiFPN)  Swin TransformerV2

关于我们 | 联系我们 | 投诉建议 | 隐私保护 | 用户协议

您是第26528467位访问者    渝ICP备15012534号-2

版权所有:《包装工程》编辑部 2014 All Rights Reserved

邮编:400039 电话:023-68795652 Email: designartj@126.com

    

渝公网安备 50010702501716号

引用本文:
【打印本页】   【下载PDF全文】   查看/发表评论  【EndNote】   【RefMan】   【BibTex】
←前一篇|后一篇→ 过刊浏览    高级检索
本文已被:浏览次   下载  
分享到: 微信 更多
摘要:
关键词:  
DOI:
分类号:
基金项目:
Abstract:
Key words:  

关于我们 | 联系我们 | 投诉建议 | 隐私保护 | 用户协议

您是第26536292位访问者    渝ICP备15012534号-2

版权所有:《包装工程》编辑部 2014 All Rights Reserved

邮编:400039 电话:023-68795652 Email: designartj@126.com

    

渝公网安备 50010702501716号