基于改进卷积神经网络的多种植物叶片病害识别  

Recognition of multiple plant leaf diseases based on improved convolutional neural network

作　　者：孙俊[1] 谭文军 毛罕平[2] 武小红[1] 陈勇[1] 汪龙 

机构地区：[1]江苏大学电气信息工程学院,镇江212013 [2]江苏大学江苏省现代农业装备与技术重点实验室,镇江212013

出　　处：《农业工程学报》2017年第19期209-215,共7页Transactions of the Chinese Society of Agricultural Engineering

基　　金：国家自然科学基金资助项目(No.31471413);江苏高校优势学科建设工程资助项目PAPD(苏政办发2011 6号);江苏省六大人才高峰资助项目(ZBZZ-019);江苏大学大学生科研立项资助项目(Y15A039);江苏大学大学生实践创新训练项目(No.46)

摘　　要：针对训练收敛时间长,模型参数庞大的问题,该文将传统的卷积神经网络模型进行改进,提出一种批归一化与全局池化相结合的卷积神经网络识别模型。通过对卷积层的输入数据进行批归一化处理,以便加速网络收敛。进一步缩减特征图数目,并采用全局池化的方法减少特征数。通过设置不同尺寸的初始层卷积核和全局池化层类型,以及设置不同初始化类型和激活函数,得到8种改进模型,用于训练识别14种不同植物共26类病害并选出最优模型。改进后最优模型收敛时间小于传统卷积神经网络模型,仅经过3次训练迭代,就能达到90%以上的识别准确率;参数内存需求仅为2.6 MB,平均测试识别准确率达到99.56%,查全率和查准率的加权平均分数为99.41%。改进模型受叶片的空间位置的变换影响较小,能识别多种植物叶片的不同病害。该模型具有较高的识别准确率及较强的鲁棒性,该研究可为植物叶片病害的识别提供参考。Plant leaf diseases are a serious problem in agricultural production. To solve this problem and prevent diseases deterioration, accurate identification of diseases types is of great significance. In this paper, we proposed a recognition model of plant leaf diseases based on convolutional neural network （CNN）, which combines the batch normalization and global pooling methods. The parameters of the traditional CNN model are large and have difficulty to converge. The proposed model was modified in the traditional structure of the CNN, which could optimize the training time and achieve the higher accuracy, and also reduce the size of model. In order to speed up the training convergence, we used the batch normalization layers. We put the input of every convolutional layer in batch, calculated the mean and variance of the batch, and then normalized this batch. We reduced some feature maps of some layers and removed the last full connect layer, with the global pooling layer instead. The proposed model has 5 convolutional layers and 4 pooling layers. In the last pooling layer pool5, the same kernel size of convolutional layer Conv5 was used to take advantage of the information of Conv5’s feature map comprehensively. For the image preprocessing, we had zoomed, flipped and rotated the original pictures of dataset randomly to get the augmented dataset, and used the 80% of pictures as the train dataset and the rest as the test dataset. These pictures were quantized to 256×256 dpi for CNN training, and the original dataset and augmented dataset were used to train models. To look for the best size of the first layer kernel, in the first convolutional layer, different kernel sizes i.e. 11×11, 9×9 and 7×7 dpi were used respectively. Furthermore, we chose the type of global pooling layer, like max pooling and average pooling. Then we designed 8 models with different Conv1 kernel sizes or global pooling types. To further improve the efficiency of this model, besides using the Gaussian initialization, we used the other c

关 键 词：病害 植物 图像处理 识别 卷积神经网络 批归一化 全局池化 深度学习 

分 类 号：S126[农业科学—农业基础科学]