基于迁移学习的番茄病虫害检测
|
摘要
为对番茄病虫害叶片特征进行提取,减少番茄病虫害叶片图像模型复杂度,缓和卷积神经网络模型检测番茄病虫害叶片图像时出现的过拟合现象,提出一种利用迁移学习技术实现卷积神经网络的分类模型,利用训练成熟的卷积网络的多层结构将底层特征逐步提升为抽象的高层特征,使其具有良好的特征学习能力。实现番茄病虫害叶片图片的数据增强,对数据增强后的叶片图片进行特征提取,利用支持向量机对图片进行分类。实验结果表明,该方法在番茄病虫害检测中具有较高的准确性和鲁棒性。
To extract the leaf table features of tomato pests and diseases,to reduce the complexity of leaf table picture model of tomato pests and diseases,and to mitigate the occurrence of over-fitting phenomena when using the convolution neural network model detects the leaf table pictures of tomato pests and diseases,a classification model of convolutional neural network was proposed using the transfer learning technique,and the multi-layer structure of well-trained convolutional network was used to elevate the underlying features into abstract high-level features,so that it has good characteristic learning ability.The images of tomato pests and diseases were enhanced,feature extraction was carried out,and the images were classified using support vector machine.Experimental results show that the proposed method has high accuracy and robustness in tomato pest detection.
To extract the leaf table features of tomato pests and diseases,to reduce the complexity of leaf table picture model of tomato pests and diseases,and to mitigate the occurrence of over-fitting phenomena when using the convolution neural network model detects the leaf table pictures of tomato pests and diseases,a classification model of convolutional neural network was proposed using the transfer learning technique,and the multi-layer structure of well-trained convolutional network was used to elevate the underlying features into abstract high-level features,so that it has good characteristic learning ability.The images of tomato pests and diseases were enhanced,feature extraction was carried out,and the images were classified using support vector machine.Experimental results show that the proposed method has high accuracy and robustness in tomato pest detection.
引文
[1]WANG Jingjing,ZHANG Wu,LIU Lianzhong,et al.Summary of crop diseases and pests image recognition technology[J].Computer Engineering and Science,2014,36(7):1363-1370(in Chinese).[汪京京,张武,刘连忠,等.农作物病虫害图像识别技术的研究综述[J].计算机工程与科学,2014,36(7):1363-1370.]
[2]WEI Zhiyi.Plant disease detection based on visible images and convolutional neural network[D].Harbin:Harbin Institute of Technology,2017(in Chinese).[卫智熠.基于卷积神经网络的可见光图像农作物病虫害的检测[D].哈尔滨:哈尔滨工业大学,2017.]
[3]ZHANG Jianhua,KONG Fantao,WU Jianzhai,et al.Cotton disease identification model based on improved VGG convolution neural network[J].Journal of China Agricultural University,2018,23(11):161-171(in Chinese).[张建华,孔繁涛,吴建寨,等.基于改进VGG卷积神经网络的棉花病害识别模型[J].中国农业大学学报,2018,23(11):161-171.]
[4]GAO Yawen,WANG Yiru,DUAN Zheng,et al.Sorting system for seed cotton fiber based on muti-information fusion[J].Industrial Control Computer,2018,31(2):46-47(in Chinese).[高雅文,王忆如,段峥,等.基于多信息融合的籽棉异纤识别分拣系统设计与实现[J].工业控制计算机,2018,31(2):46-47.]
[5]REN Jingjing.Image blurring based on convolution neural network[D].Hefei:Anhui University,2017(in Chinese).[任静静.基于卷积神经网络的图像模糊去除[D].合肥:安徽大学,2017.]
[6]SUN Hongjie.Grape variety identification method based on leaf image analysis[D].Xianyang:Northwest Agriculture and Forestry University,2016(in Chinese).[孙宏杰.基于叶片图像分析的葡萄品种识别方法研究[D].咸阳:西北农林科技大学,2016.]
[7]Valiente D,Gil A,Fernández L,et al.A comparison of EKFand SGD applied to a view-based SLAM approach with omnidirectional images[J].Robotics&Autonomous Systems,2014,62(2):108-119.
[8]WU Zhengwen.Application of convolution neural network in image classification[D].Chengdu:University of Electronic Science and Technology,2015.(in Chinese).[吴正文.卷积神经网络在图像分类中的应用研究[D].成都:电子科技大学,2015.]
[9]Maitra D S,Bhattacharya U,Parui S K.CNN based common approach to handwritten character recognition of multiple scripts[C]//International Conference on Document Analysis and Recognition.China:IEEE,2015:1021-1025.
[10]PAN Mingxing,FENG Xiangwen,SUN Jian,et al.A method of character recognition based on deep learning[P].Jiangsu:CN106446954A,2017-02-22.(in Chinese)[潘铭星,冯向文,孙健,等.一种基于深度学习的字符识别方法[P].江苏:CN106446954A,2017-02-22.]
[11]HU Yin,HUANG Qiquan.Application of deep learning in identity card character recognition[J].Digital World,2018(3):44-45(in Chinese).[胡胤,黄启权.深度学习在身份证字符识别中的应用研究[J].数码世界,2018(3):44-45.]
[2]WEI Zhiyi.Plant disease detection based on visible images and convolutional neural network[D].Harbin:Harbin Institute of Technology,2017(in Chinese).[卫智熠.基于卷积神经网络的可见光图像农作物病虫害的检测[D].哈尔滨:哈尔滨工业大学,2017.]
[3]ZHANG Jianhua,KONG Fantao,WU Jianzhai,et al.Cotton disease identification model based on improved VGG convolution neural network[J].Journal of China Agricultural University,2018,23(11):161-171(in Chinese).[张建华,孔繁涛,吴建寨,等.基于改进VGG卷积神经网络的棉花病害识别模型[J].中国农业大学学报,2018,23(11):161-171.]
[4]GAO Yawen,WANG Yiru,DUAN Zheng,et al.Sorting system for seed cotton fiber based on muti-information fusion[J].Industrial Control Computer,2018,31(2):46-47(in Chinese).[高雅文,王忆如,段峥,等.基于多信息融合的籽棉异纤识别分拣系统设计与实现[J].工业控制计算机,2018,31(2):46-47.]
[5]REN Jingjing.Image blurring based on convolution neural network[D].Hefei:Anhui University,2017(in Chinese).[任静静.基于卷积神经网络的图像模糊去除[D].合肥:安徽大学,2017.]
[6]SUN Hongjie.Grape variety identification method based on leaf image analysis[D].Xianyang:Northwest Agriculture and Forestry University,2016(in Chinese).[孙宏杰.基于叶片图像分析的葡萄品种识别方法研究[D].咸阳:西北农林科技大学,2016.]
[7]Valiente D,Gil A,Fernández L,et al.A comparison of EKFand SGD applied to a view-based SLAM approach with omnidirectional images[J].Robotics&Autonomous Systems,2014,62(2):108-119.
[8]WU Zhengwen.Application of convolution neural network in image classification[D].Chengdu:University of Electronic Science and Technology,2015.(in Chinese).[吴正文.卷积神经网络在图像分类中的应用研究[D].成都:电子科技大学,2015.]
[9]Maitra D S,Bhattacharya U,Parui S K.CNN based common approach to handwritten character recognition of multiple scripts[C]//International Conference on Document Analysis and Recognition.China:IEEE,2015:1021-1025.
[10]PAN Mingxing,FENG Xiangwen,SUN Jian,et al.A method of character recognition based on deep learning[P].Jiangsu:CN106446954A,2017-02-22.(in Chinese)[潘铭星,冯向文,孙健,等.一种基于深度学习的字符识别方法[P].江苏:CN106446954A,2017-02-22.]
[11]HU Yin,HUANG Qiquan.Application of deep learning in identity card character recognition[J].Digital World,2018(3):44-45(in Chinese).[胡胤,黄启权.深度学习在身份证字符识别中的应用研究[J].数码世界,2018(3):44-45.]