基于计算机视觉与机器学习的烟丝杂质图像级联检测方法
Research on cascade detection technology of tobacco impurities images based on computer vision and machine learning
-
摘要: 为提高烟丝杂质检测及剔除的准确率,设计了一种基于计算机视觉与机器学习的烟丝杂质图像级联检测方法。该方法采用颜色特征和梯度能量计算机视觉方法对烟丝杂质进行定位,结合HOG特征、LBP特征与级联Adaboost分类器,设计多窗口检测算法对烟丝杂质进行实时检测。结果表明:基于颜色特征的静态杂质检测方法的准确率高于梯度能量方法,在结合了HOG特征和级联Adaboost分类器算法后,检测结果非常稳定,烟丝杂质检测准确率达到97.33%,在实际操作过程中不需要人工调整算法参数,在保证算法准确率和有效性的同时降低了时间成本。
-
关键词:
- 烟丝杂质检测 /
- 计算机视觉 /
- 多窗口检测 /
- 级联Adaboost分类器 /
- 颜色特征
Abstract: To improve the accuracy of tobacco impurity detection and removal, a cascade detection method for tobacco impurity images based on computer vision and machine learning was designed. This method used color features and gradient energy computer vision methods to locate tobacco impurities. Combining HOG and LBP features with a cascade Adaboost classifier, a multi-window detection algorithm was designed to detect tobacco impurities in real time. The experimental results showed that the accuracy of the static impurity detection method based on color features was higher than that of the gradient energy method. After combining HOG features and multi-level cascade Adaboost classifier algorithm, the detection results were very stable, and the accuracy of tobacco impurity detection reached 97.33%. In the actual operation process, there was no need to manually adjust the algorithm parameters, ensuring the accuracy and effectiveness of the algorithm while reducing the time cost. -
-
[1]
杨秉佐, 张建新, 孙文杰, 等.智能化技术在烟草检测设备中的应用[J].电子技术与软件工程, 2021(14):170-171.
-
[2]
林云, 欧阳璐斯, 赖燕华, 等.基于霉菌酵母测试片和NIR技术快速鉴别霉变烟草最优势霉菌种类[J].食品工业科技, 2021, 42(23):280-286.
-
[3]
陈然, 张大波, 卓浩廉, 等.提升管中烟丝运动速度的定量检测及其运动特性分析[J].烟草科技, 2021, 54(8):71-79.
-
[4]
VILLANTI A C, LEPINE S E, WEST J C, et al.Identifying message content to reduce vaping:Results from online message testing trials in young adult tobacco users[J].Addictive Behaviors, 2021, 115:106778.
-
[5]
李丽霞.烟草恒温恒湿实验室用无线环境检测设备的研究[J].计量与测试技术, 2020, 47(1):39-41.
-
[6]
孙晶.基于图像识别技术的消费者卷烟品牌培育路径的研究[J].科技创新与应用, 2019(9):141-143.
-
[7]
李晓, 袁帅, 姚二民, 等.基于片烟图像处理面积及feret直径的分形分析[J].烟草科技, 2020, 53(2):80-87.
-
[8]
张红涛, 刘迦南, 谭联, 等.基于机器视觉的烟青虫和棉铃虫雌雄蛹的分类识别[J].烟草科技, 2020, 53(2):21-26.
-
[9]
ZHANG Y, ZHANG J.Machine vision system for visual defect inspection of TFT-LCD[J].Journal of Harbin Institute of Technology, 2007, 14(6):773-778.
-
[10]
WANG H L, HAN J Q, HAI-FENG L I.SVM with discriminative dynamic time alignment[J].Journal of Harbin Institute of Technology, 2007, 14(5):598-603.
-
[11]
刘浩, 贺福强, 李荣隆, 等.基于机器视觉的卷烟小盒商标纸表面缺陷在线检测技术[J].中国烟草学报, 2020, 26(5):54-59.
-
[12]
王伟, 朱立明, 章强, 等.基于相似性分析和阈值自校正的烟箱缺条智能检测方法[J].烟草科技, 2019, 52(1):91-97.
-
[13]
王惠, 赵世民, 叶红朝, 等.基于图像处理的烟草分级系统设计与实现[J].现代农业科技, 2018(17):289-291.
-
[14]
李绍坚, 于立军, 王国立, 等.形态学图像处理在缺支检测中的应用[J].科技资讯, 2011(36):251.
-
[15]
KUMAR S S, GANESAN L.Texture classification using wavelet based laws energy measure[J].International Journal of Soft Computing, 2012, 3(4):293-296.
-
[16]
张璐.浅析烟草商业企业"互联网+"创新建设思路[J].中国市场, 2019(13):166169.
-
[17]
汪强, 席磊, 任艳娜, 等.基于计算机视觉技术的烟叶成熟度判定方法[J].农业工程学报, 2012, 28(4):175-179.
-
[18]
ZHANG F, TASHPOLAT T, KUNG H, et al.Method of soil salinization information extraction with SVM classification based on ica and texture features[J].Agricultural Science & Technology, 2011, 12(7):1046-1049, 1074.
-
[19]
张绍堂, 董德春, 任友俊, 等.烟草异物剔除系统中典型异物处理方法[J].烟草科技, 2009, (5):22-25.
-
[20]
涂平平.烟草异物剔除系统相关算法的研究[D].南京:东南大学, 2016.
-
[21]
张绍堂, 蒋作, 郑智捷.机器视觉技术在烟草异物剔除系统中的应用[J].云南民族大学学报(自然科学版), 2007, 16(2):161-164.
-
[22]
姜炬达.烟草异物除杂机信号处理系统设计[D].南京:南京理工大学, 2014.
-
[23]
常金强, 张若宇, 庞宇杰, 等.高光谱成像的机采籽棉杂质分类检测[J].光谱学与光谱分析, 2021, 41(11):3552-3558.
-
[24]
陈进, 张帅, 李耀明, 等.联合收获机水稻破碎籽粒及杂质在线识别方法[J].中国农机化学报, 2021, 42(6):137-144.
-
[25]
王飞, 靳向煜.基于边缘检测的原棉杂质图像识别方法适用性分析[J].现代纺织技术, 2019, 27(5):39-43.
-
[26]
孙绍晟, 张林.基于图像的牛奶细微杂质检测算法研究与仿真[J].计算机应用与软件, 2022, 30(1):281-283
, 314.
-
[1]
计量
- PDF下载量: 61
- 文章访问数: 3473
- 引证文献数: 0