Crop leaf disease recognition based on feature-level and decision-level fusion
WANG Ziheng1, SHEN Jifeng1, ZUO Xin2, WU Xiaohong1, SUN Jun1
1. School of Electrical and Information Engineering, Jiangsu University, Zhenjiang， Jiangsu 212013, China； 2. School of Computer, Jiangsu University of Science and Technology, Zhenjiang， Jiangsu 212003, China
Abstract：To solve the shortcomings of single-network model with learning preference for data， the crop disease identification method was proposed based on multi-model fusion. The single model performance of four mainstream convolutional neural networks of ResNet50, DenseNet121, Xception and MobileNetV2 was evaluated by the proposed method, and the four single models were respectively conducted by multi-model feature-level and decision-level fusion to obtain the identification output. The feature-level fusion method was used to average, maximize and splice the final output feature layer of each sub-network to achieve efficient complementarity of heterogeneous features. The decision-level fusion method was used to maximize and average the output probability of each sub-network to achieve efficient union of probability distribution decisions. The experimental results on the PDR2018 crop disease datasets show that feature-level fusion outperforms decision-level fusion and single-model methods significantly. Among the fusion methods, splicing compression feature fusion achieves the highest recognition accuracy of 98.44%. The cross-database experiments on PlantDoc data subset and the actual images confirm that the feature fusion method exhibits superior accuracy and generalization performance compared to the single-model method.
JIA S P, GAO H J, HANG X. Researchprogress on ima-ge recognition technology of crop pests and diseases based on deep learning [J]. Transactions of the CSAM, 2019,50(Sup1)：313-317.(in Chinese)
ZHANG L K,XIAO D Q,CEN G J,et al.Individual plant extraction and counting from field images based on leaf matching [J].Journal of Jiangsu University(Natural Science Edition),2023,44(3):293-301.(in Chinese)
ZHANG S W,ZHANG C L. Maize disease recognition based on local discriminant algorithm [J]. Transactions of the CSAE, 2014,30(11):167-172.(in Chinese)
［6］
PADOL P B, YADAV A A. SVM classifier based grape leaf disease detection [C]∥2016 Conference on Advances in Signal Processing, 2016:175-179.
［7］
SURESHA M, SHREEKANTH K N, THIRUMALESH B V. Recognition of diseases in paddy leaves using KNN classifier [C]∥2017 2nd International Conference for Convergence in Technology, 2017:663-666.
［8］
SABROL H, SATISH K. Tomato plant disease classification in digital images using classification tree [C]∥2016 International Conference on Communication and Signal Processing, 2016:1242-1246.
CHEN Y S，GENG C X，WANG Y，et al. Center line extraction of paddy seedling row based on segmented vertical projection [J].Journal of Jiangsu University(Natural Science Edition),2022,43(3):289-295.(in Chinese)
SU S F, QIAO Y, RAO Y.Recognition of grape leaf di-seases and mobile application based on transfer learning [J]. Transactions of the CSAE, 201,37(10):127-134.(in Chinese)
［11］
KRIZHEVSKY A, SUTSKEVER I, HINTON G E. Imagenet classification with deep convolutional neural networks [J]. Advances in Neural Information Processing Systems, 2012,60：25-33.
［12］
LYU M, ZHOU G, HE M, et al. Maize leaf disease identification based on feature enhancement and DMS-robust alexnet [J]. IEEE Access, 2020,8:57952-57966.
SUN J, TAN W J, MAO H P, et al. Real-time recognition of sugar beet and weeds in complex backgrounds using multi-channel depth-wise separable convolution model [J]. Transactions of the CSAE, 2017,33(19)：209-215.(in Chinese)
［14］
SIMONYAN K, ZISSERMAN A.Very deep convolutional networks for large-scale image recognition [J]. Computer Science,2014，6:113-123.
ZHANG J H,KONG F T,WU J Z,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)
［16］
NAGARAJU Y, SWETHA S, STALIN S. Apple and grape leaf diseases classification using transfer learning via fine-tuned classifier [C]∥2020 IEEE International Conference on Machine Learning and Applied Network Technologies, 2020:1-6.
［17］
HE K, ZHANG X, REN S, et al. Deep residual lear-ning for image recognition [C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition， 2016:770-778.
［18］
LI X, RAI L. Apple leaf disease identification and classification using resnet models [C]∥2020 IEEE 3rd International Conference on Electronic Information and Communication Technology, 2020:738-742.
［19］
SZEGEDY C, LIU W, JIA Y, et al. Going deeper with convolutions [C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition， 2015:1-9.
［20］
HUANG G, LIU Z, VAN DER MAATEN L, et al. Densely connected convolutional networks [C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017:4700-4708.
［21］
SZEGEDY C, VANHOUCKE V, IOFFE S, et al. Rethinking the inception architecture for computer vision [C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition， 2016:2818-2826.
［22］
KEH S S. Semi-supervised noisy student pre-training on efficientnet architectures for plant pathology classification [J]. arXiv， DOI：10.48550/arXiv.2012.00332.
［23］
KENDLER S, AHARONI R, YOUNG S, et al. Detection of crop diseases using enhanced variability imagery data and convolutional neural networks [J]. Computers and Electronics in Agriculture, 2022,193:1-8.
REN Y M,YANG J,GUO Z Q,et al.Self-adaptive entropy weighted decision fusion method for ship image classification based on multi-scale convolutional neural network [J].Journal of Electronics and Information Techno-logy, 2021,43(5):1424-1431.(in Chinese)
LI H,WANG B.Deep feature fusion method and its application in leaf disease recognition [J].Computer Systems & Applications,2022,31(7):349-355.(in Chinese)
MA Y K,LIU Z Q,ZHANG W W,et al.Image recognition of crop disease based on multi-feature fusion [J].Journal of Henan Institute of Science and Technology(Natural Science Edition),2021,49(4):45-50，57.(in Chinese)
DU Z K，FANG S，LI Z，et al.Tomato leaf disease detection based on deep feature fusion of convolution neural network [J]. China Science Paper,2021,16(7):701-707.(in Chinese)
［28］
CHOLLET F. Xception:deep learning with depthwise separable convolutions [C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition， 2017:1251-1258.
［29］
SANDLER M, HOWARD A, ZHU M， et al. MobileNetV2: inverted residuals and linear bottlenecks [C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition， 2018:4510-4520.
［30］
ZHOU B, KHOSLA A, LAPEDRIZA A, et al. Learning deep features for discriminative localization [C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition， 2016:2921-2929.
WANG M H,WU Z X,ZHOU Z G.Fine-grained identification research of crop pests and diseases based on improved CBAM via attention [J].Transactions of the CSAM,2021,52(4):239-247.(in Chinese)
SUN J, ZHU W D, LUO Y Q, et al. Recognizing the diseases of crop leaves in fields using improved MobileNet-V2 [J]. Transactions of the CSAE,2021,37(22):161-169.(in Chinese)
［33］
BEHERA A, WHARTON Z, HEWAGE P R P G, et al. Context-aware attentional pooling (cap) for fine-grained visual classification [C]∥Proceedings of the AAAI Conference on Artificial Intelligence，2021,35(2):929-937.
2024, Vol. 45 
