DCNN Transfer Learning and Multi-model Integration for Disease and Weed Identification

For the complex image segmentation problem and high complexity of model caused by digital processing technology, we first use data enhancement technology to expand dataset size, and then use deep convolutional neural networks (CNNs) multi-model integration method combined transfer learning to identify crop disease and weed. On the one hand, we make full use of the prior knowledge learned from big dataset of four single deep CNNs (VGG, Inception-v3, ResNet and DenseNet). By parameter fine-tuning, the CNNs are reused in the agricultural field to alleviate the over-fitting problem caused by insufficient data sources. On the other hand, two or more CNNs are combined by the direct average method to complete multi-model integration. We directly average the category confidence generated by different models to obtain the final prediction result. The experimental results show that the combination of deep CNNs and transfer learning is effective and the CNNs multi-model integration method can further improve the identification accuracy compared to the single CNN model. The validation accuracy of crop disease and weed dataset can reach 97.14% and 99.22% respectively by using multi-model integration and transfer learning.

[1]  Murvet Kirci,et al.  Disease detection on the leaves of the tomato plants by using deep learning , 2017, 2017 6th International Conference on Agro-Geoinformatics.

[2]  Jinghui Li,et al.  Extraction and analysis of digital images feature of three kinds of wheat diseases , 2010, 2010 3rd International Congress on Image and Signal Processing.

[3]  Itir Önal,et al.  Treelogy: A Novel Tree Classifier Utilizing Deep and Hand-crafted Representations , 2017, ArXiv.

[4]  David Jones,et al.  Intensified fuzzy clusters for classifying plant, soil, and residue regions of interest from color images , 2004 .

[5]  Pablo M. Granitto,et al.  Deep learning for plant identification using vein morphological patterns , 2016, Comput. Electron. Agric..

[6]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[7]  Yu Sun,et al.  Automatic Image-Based Plant Disease Severity Estimation Using Deep Learning , 2017, Comput. Intell. Neurosci..

[8]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[10]  Mostafa Mehdipour-Ghazi,et al.  Plant identification using deep neural networks via optimization of transfer learning parameters , 2017, Neurocomputing.

[11]  David Hughes,et al.  Deep Learning for Image-Based Cassava Disease Detection , 2017, Front. Plant Sci..

[12]  Daniele Nardi,et al.  Fast and Accurate Crop and Weed Identification with Summarized Train Sets for Precision Agriculture , 2016, IAS.

[13]  Yang Xu,et al.  Weed identification based on K-means feature learning combined with convolutional neural network , 2017, Comput. Electron. Agric..

[14]  Hitoshi Iyatomi,et al.  Basic Study of Automated Diagnosis of Viral Plant Diseases Using Convolutional Neural Networks , 2015, ISVC.

[15]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Ricardo Matsumura de Araújo,et al.  Classification of Apple Tree Disorders Using Convolutional Neural Networks , 2016, 2016 IEEE 28th International Conference on Tools with Artificial Intelligence (ICTAI).

[17]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Changshui Zhang,et al.  An In-field Automatic Wheat Disease Diagnosis System , 2017, Comput. Electron. Agric..