计算机视觉检测技术在菌群计数领域的应用研究
Journal: Advances in Computer and Autonomous Intelligence Research DOI: 10.12238/acair.v2i4.10290
Abstract
在食品检验检测领域,对微生物菌群的培养后计数是出具权威检测报告的关键指标。该研究开发了一种基于深度学习的高效、端到端的菌群计算机视觉检测方法。首先,该研究收集了近2000张菌群图像样本,并进行人工分类和标记,形成大数据量训练集。然后,构建了优化后的YOLOv7模型,优化项主要是增设了小目标检测层,开发了含标注数据的图像增强方法,并采用K-means方法对anchor进行了优化计算。最后,通过云服务器训练模型并取得最优参数,并开发菌群视觉检测管理信息系统,在企业中试运行,对模型性能进行了评估。结果表明,优化后的模型mAP@.5增长了4.5%,模型的全类别F1-score平均达到88.5%,主要类别F1-score达到87.3%。该研究给出了一套食品检验检测领域菌群计数的整体解决方案,市场化应用具备无缝接入条件。
Keywords
视觉检测；深度学习；卷积神经网络；菌群计数
Funding
2022年甘肃省科技厅重点研发项目-社会发展类,“基于大数据分析技术的商检食品安全及增值应用平台建设”(22YF7FA068)。
Full Text
PDF - Viewed/Downloaded: 0 TimesReferences
[1] J.Zhangetal.,"Acomprehensivereviewofimageanalysismethodsfor microorganism counting:from classical image proces singto deep learning approaches,"Artificial Intelligence Review, vol.55,pp.2875-2944,Sep.2021,doi:10.1007/s10462-021-10082-4.
[2] Zhang,C.,Chen,W.B.,Liu,W.L.,&Chen,C.B.(2010).Anautomated bacterial colony counting system.In2010 3rd International Congress on Image and Signal Processing (Vol.4,pp.1819-1823).
[3] Otsu,N.(1979).Athreshold selection method from graylevel histograms.IEEE Transactions on Systems,Man, and Cybern etics,9(1),62-66.
[4] J.Rimal et al.,"Risk assessment of smokeless tobacco among oral precancer and cancer patients in eastern develo pmental region of Nepal,"Asian PacificJ.CancerPrevention,vol. 20,no.2,2019.
[5] H.Gelband et al.,Disease Control Priorities:Cancer, Wor ld Bank,2015.
[6] Barbedo,J. G. A. (2012). Unified framework for counting agriculture-related objects in digital images. Embrapa Infor mática Agropecuária-Artigo em anais de congresso (ALICE), In: CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES,25.,2012,Ouro Preto.
[7] Ferrari,A.,Lombardi, S.,& Signoroni, A. (2015). Bacterial colony counting by convolutional neural networks. In 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)(pp.7458-7461).IEEE.
[8] Tamiev,D., Furman, P. E., & Reuel, N. F. (2020). Automated classification of bacterial cell sub-populations with convol utional neural networks.PLoS ONE,15(10),e0241200.
[9] J.Redmon et al., "You only look once: Unified, real-time object detection,"in Proc.IEEE Conf.Comput.Vis.PatternRecognit.(CVPR),2016.
[10] S.Ren et al., "Faster R-CNN: Towards real-time object detection with region proposal networks," in Proc. Adv. Neural Inf.Process.Syst.,2015.
[11] K.He etal.,"Mask R-CNN,"in Proc.IEEE Int.Conf. Comput. Vis.,2017.
[12] A.Krizhevsky etal.,"ImageNet classification with de ep convolutional neural networks,"inProc.Adv.NeuralInf.Proce ss.Syst.,2012.
[2] Zhang,C.,Chen,W.B.,Liu,W.L.,&Chen,C.B.(2010).Anautomated bacterial colony counting system.In2010 3rd International Congress on Image and Signal Processing (Vol.4,pp.1819-1823).
[3] Otsu,N.(1979).Athreshold selection method from graylevel histograms.IEEE Transactions on Systems,Man, and Cybern etics,9(1),62-66.
[4] J.Rimal et al.,"Risk assessment of smokeless tobacco among oral precancer and cancer patients in eastern develo pmental region of Nepal,"Asian PacificJ.CancerPrevention,vol. 20,no.2,2019.
[5] H.Gelband et al.,Disease Control Priorities:Cancer, Wor ld Bank,2015.
[6] Barbedo,J. G. A. (2012). Unified framework for counting agriculture-related objects in digital images. Embrapa Infor mática Agropecuária-Artigo em anais de congresso (ALICE), In: CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES,25.,2012,Ouro Preto.
[7] Ferrari,A.,Lombardi, S.,& Signoroni, A. (2015). Bacterial colony counting by convolutional neural networks. In 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)(pp.7458-7461).IEEE.
[8] Tamiev,D., Furman, P. E., & Reuel, N. F. (2020). Automated classification of bacterial cell sub-populations with convol utional neural networks.PLoS ONE,15(10),e0241200.
[9] J.Redmon et al., "You only look once: Unified, real-time object detection,"in Proc.IEEE Conf.Comput.Vis.PatternRecognit.(CVPR),2016.
[10] S.Ren et al., "Faster R-CNN: Towards real-time object detection with region proposal networks," in Proc. Adv. Neural Inf.Process.Syst.,2015.
[11] K.He etal.,"Mask R-CNN,"in Proc.IEEE Int.Conf. Comput. Vis.,2017.
[12] A.Krizhevsky etal.,"ImageNet classification with de ep convolutional neural networks,"inProc.Adv.NeuralInf.Proce ss.Syst.,2012.
Copyright © 2024 张武, 郭文斌, 尤毅娜, 杨光瑞, 金莹
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License