基于Caffe的生姜病害识别系统研究与设计
|
摘要
以自然环境下采集到的生姜病害图片为基础,对炭疽病、姜瘟病、根结线虫病和白星病进行研究分析,提出一种基于卷积神经网络的生姜病害识别系统。首先是对收集来的图片进行二值化和轮廓分割等预处理,从而增强数据的可靠性。其次,将处理后的图像数据交由优化后的卷积神经网络模型进行分析、学习,并在Caffe框架下进行模拟仿真。最后,在已训练好的网络模型基础上利用Qt软件设计人机交互界面,从而达到数据可视化提高系统使用的便捷性。结果表明优化后的模型识别率达到了96%,可以较好地预测和识别生姜的相关病害。
Based on the images of ginger diseases collected in natural environment,anthracnose,ginger blast,root knot nematode and white star disease were studied and analyzed.A ginger disease recognition system based on convolution neural network was proposed.Firstly,the collected images were pre-processed by binarization and contour segmentation,so as to enhance the reliability of the data.Secondly,the processed image data were handed over to the optimized convolutional neural network model for analysis and learning,and simulated in the framework of Caffe.Finally,on the basis of the trained network model,it was used Qt software to design human-computer interaction interface,so as to achieve data visualization and improve the convenience of the system.The results showed that the recognition rate of the optimized model reached 96%.The system can better predict and identify the related diseases of ginger.
Based on the images of ginger diseases collected in natural environment,anthracnose,ginger blast,root knot nematode and white star disease were studied and analyzed.A ginger disease recognition system based on convolution neural network was proposed.Firstly,the collected images were pre-processed by binarization and contour segmentation,so as to enhance the reliability of the data.Secondly,the processed image data were handed over to the optimized convolutional neural network model for analysis and learning,and simulated in the framework of Caffe.Finally,on the basis of the trained network model,it was used Qt software to design human-computer interaction interface,so as to achieve data visualization and improve the convenience of the system.The results showed that the recognition rate of the optimized model reached 96%.The system can better predict and identify the related diseases of ginger.
引文
[1]吴星,赵虎,王萌,等.广西塑料大棚彩椒套种包心芥菜安全高产栽培技术[J].北方园艺,2016(19):204-206.
[2]金伟林.芥菜的营养价值及高产高效栽培技术[J].蔬菜,2014(6):40-41.
[3]李井祝,王鹏,耿长兴.基于图像处理的黄瓜霜霉病情评估[J].中国农机化学报,2017,38(6):67-71.Li Jingzhu,Wang Peng,Geng Changxing.Disease assessment of cucumber downy mildew based on image processing[J].Journal of Chinese Agricultural Mechanization,2017,38(6):67-71.
[4]李剑辉.大肉包心芥菜高产优质栽培技术探究[J].农技服务,2016,33(5):79.
[5]许良凤,徐小兵,胡敏,等.基于多分类器融合的玉米叶部病害识别[J].农业工程学报,2015,31(14):194-201.Xu Liangfeng Xu Xiaobing Hu Min,et al.Corn leaf disease identification based on multiple classifiers fusion[J].Transactions of the Chinese Society of Agricultural Engineering,2015,31(14):194-201.
[6]孙俊,谭文军,毛罕平,等.基于改进卷积神经网络的多种植物叶片病害识别[J].农业工程学报,2017,33(19):209-215.Sun Jun,Tan Wenjun,Mao Hanping,et al.Recognition of multiple plant leaf diseases based on improved convolutional neural network[J].Transactions of the Chinese Society of Agricultural Engineering,2017,33(19):209-215.
[7]胡鹏程,郭焱,李保国,等.基于多视角立体视觉的植株三维重建与精度评估[J].农业工程学报,2015,31(11):209-214.Hu Pengcheng,Guo Yan,Li Baoguo,et al.Three-dimensional reconstruction and its precision evaluation of plant architecture based on multiple view stereo method[J].Transactions of the Chinese Society of Agricultural Engineering,2015,31(11):209-214.
[8]Zaman F,Wong Y P,Yian Ng B.Density-based denoising of point cloud[C].9th International Conference on Robotic,Vision,Signal Processing and Power Applications,Springer,Singapore,2017.
[9]尹宏鹏,陈波,柴毅,等.基于视觉的目标检测与跟踪综述[J].自动化学报,2016,42(10):1466-1489.
[10]Xu S,Yang Z,Wu W.Algorithm of 3Dreconstruction based on point cloud segmentation denoising[C].International Conference on Information Science and Engineering,IEEE,2011.
[11]常春,陈怡群,肖宏儒,等.基于神经网络图像分析的智能鲜茶叶分选机[J].中国农机化学报,2013,34(1):137-141.Chang Chun,Chen Yiqun,Xiao Hongru,et al.Smart fresh tea sorter with neural network image analysis[J].Journal of Chinese Agricultural Mechanization,2013,34(1):137-141.
[12]米硕,田丰收,孙瑞彬,等.Swish激活函数在中小规模数据集上的性能表现[J].科技创新与应用,2018(1):4-5.
[13]Francois Chollet.Deep learning with python[M].Manning Publications,2017.
[14]张占强,朝乐门,孟克其劳.基于图像分析的牛奶液位标定算法研究[J].中国农机化学报,2014,35(1):224-228.Zhang Zhanqiang,Chao Lemen,Meng Keqilao.Study on a milk liquid-level calibration algorithm using image analysis[J].Journal of Chinese Agricultural Mechanization,2014,35(1):224-228.
[15]武威,孙启洵,周平,等.稻麦叶面积指数估算系统设计[J].中国农机化学报,2017,38(9):75-78.Wu Wei,Sun Qixun,Zhou Ping,et al.Design on leaf area index estimation system of rice and wheat[J].Journal of Chinese Agricultural Mechanization,2017,38(9):75-78.
[16]Ren S,He K,Girshick R,et al.Faster R-CNN:Towardsreal-time object detection with region proposal networks[C].International Conference on Neural Information Processing Systems,MIT Press,2015.
[17]黄凯奇,任伟强,谭铁牛.图像物体分类与检测算法综述[J].计算机学报,2014,37(6):1225-1240.
[18]Khosa I,Pasero E.Defect detection in food ingredients using multilayer perceptron neural network[C].Computer Applications&Research,IEEE,2014.
[19]严贤,韩秀玲.基于Qt的串口通信应用研究与实现[J].微计算机信息,2012(8):122-124.
[20]Yao Y,Lu S,Bo H,et al.Automated chemiluminescence immunoassay analyzer[C].International Conference on Intelligent Computation Technology and Automation,IEEE Computer Society,2010.
[21]赵俊生.嵌入式Linux系统图形界面显示方法的实现[J].工业仪表与自动化装置,2014(2):53-55.
[2]金伟林.芥菜的营养价值及高产高效栽培技术[J].蔬菜,2014(6):40-41.
[3]李井祝,王鹏,耿长兴.基于图像处理的黄瓜霜霉病情评估[J].中国农机化学报,2017,38(6):67-71.Li Jingzhu,Wang Peng,Geng Changxing.Disease assessment of cucumber downy mildew based on image processing[J].Journal of Chinese Agricultural Mechanization,2017,38(6):67-71.
[4]李剑辉.大肉包心芥菜高产优质栽培技术探究[J].农技服务,2016,33(5):79.
[5]许良凤,徐小兵,胡敏,等.基于多分类器融合的玉米叶部病害识别[J].农业工程学报,2015,31(14):194-201.Xu Liangfeng Xu Xiaobing Hu Min,et al.Corn leaf disease identification based on multiple classifiers fusion[J].Transactions of the Chinese Society of Agricultural Engineering,2015,31(14):194-201.
[6]孙俊,谭文军,毛罕平,等.基于改进卷积神经网络的多种植物叶片病害识别[J].农业工程学报,2017,33(19):209-215.Sun Jun,Tan Wenjun,Mao Hanping,et al.Recognition of multiple plant leaf diseases based on improved convolutional neural network[J].Transactions of the Chinese Society of Agricultural Engineering,2017,33(19):209-215.
[7]胡鹏程,郭焱,李保国,等.基于多视角立体视觉的植株三维重建与精度评估[J].农业工程学报,2015,31(11):209-214.Hu Pengcheng,Guo Yan,Li Baoguo,et al.Three-dimensional reconstruction and its precision evaluation of plant architecture based on multiple view stereo method[J].Transactions of the Chinese Society of Agricultural Engineering,2015,31(11):209-214.
[8]Zaman F,Wong Y P,Yian Ng B.Density-based denoising of point cloud[C].9th International Conference on Robotic,Vision,Signal Processing and Power Applications,Springer,Singapore,2017.
[9]尹宏鹏,陈波,柴毅,等.基于视觉的目标检测与跟踪综述[J].自动化学报,2016,42(10):1466-1489.
[10]Xu S,Yang Z,Wu W.Algorithm of 3Dreconstruction based on point cloud segmentation denoising[C].International Conference on Information Science and Engineering,IEEE,2011.
[11]常春,陈怡群,肖宏儒,等.基于神经网络图像分析的智能鲜茶叶分选机[J].中国农机化学报,2013,34(1):137-141.Chang Chun,Chen Yiqun,Xiao Hongru,et al.Smart fresh tea sorter with neural network image analysis[J].Journal of Chinese Agricultural Mechanization,2013,34(1):137-141.
[12]米硕,田丰收,孙瑞彬,等.Swish激活函数在中小规模数据集上的性能表现[J].科技创新与应用,2018(1):4-5.
[13]Francois Chollet.Deep learning with python[M].Manning Publications,2017.
[14]张占强,朝乐门,孟克其劳.基于图像分析的牛奶液位标定算法研究[J].中国农机化学报,2014,35(1):224-228.Zhang Zhanqiang,Chao Lemen,Meng Keqilao.Study on a milk liquid-level calibration algorithm using image analysis[J].Journal of Chinese Agricultural Mechanization,2014,35(1):224-228.
[15]武威,孙启洵,周平,等.稻麦叶面积指数估算系统设计[J].中国农机化学报,2017,38(9):75-78.Wu Wei,Sun Qixun,Zhou Ping,et al.Design on leaf area index estimation system of rice and wheat[J].Journal of Chinese Agricultural Mechanization,2017,38(9):75-78.
[16]Ren S,He K,Girshick R,et al.Faster R-CNN:Towardsreal-time object detection with region proposal networks[C].International Conference on Neural Information Processing Systems,MIT Press,2015.
[17]黄凯奇,任伟强,谭铁牛.图像物体分类与检测算法综述[J].计算机学报,2014,37(6):1225-1240.
[18]Khosa I,Pasero E.Defect detection in food ingredients using multilayer perceptron neural network[C].Computer Applications&Research,IEEE,2014.
[19]严贤,韩秀玲.基于Qt的串口通信应用研究与实现[J].微计算机信息,2012(8):122-124.
[20]Yao Y,Lu S,Bo H,et al.Automated chemiluminescence immunoassay analyzer[C].International Conference on Intelligent Computation Technology and Automation,IEEE Computer Society,2010.
[21]赵俊生.嵌入式Linux系统图形界面显示方法的实现[J].工业仪表与自动化装置,2014(2):53-55.