Xinjiang is an important forest and fruit industry base in China, and the characteristic forest and fruit industry is an important part of regional economic development. In order to prevent fruit tree diseases from restricting the development of forest and fruit industry, a MobileNet-V2 NAM fruit tree leaf classification and disease identification model was designed in this study. It incorporated a lightweight normalization-based attention module to improve the model's sensitivity to feature information and make the model focus on salient features. At the same time, L1 regularization was added to the loss function to penalize the sparsity of the weights and suppress the non-significant weights. The experimental results showed that: in leaf classification, the model performed well in the classification results of self-built, Plant Village, and mixed datasets, with the accuracy rates reaching 97.05%, 98.73%, and 94.91%, respectively, and had good generalization ability. In disease identification, the MobileNet-V2 NAM model achieved a recognition accuracy of 94.55%, which was higher than the AlexNet, VGG16 classic CNN models, and the number of parameters of the model was only 3.56M. MobileNet-V2 NAM has good accuracy while maintaining a low amount of model parameters, provides technical support for embedding deep learning models into mobile devices.
HUD Y, HUANGL P, GAOJ,et al.Study on the countermeasures for promoting the development of forestry and fruit industry mechanization in Xinjiang[J].Journal of Chinese Agricultural Mechanization,2021,42(4):211-216,222.
[3]
BAOW, YANGX, LIANGD,et al.Lightweight convolutional neural network model for field wheat ear disease identification[J].Computers and Electronics in Agriculture,2021,189:106367.
[4]
PICONA, SEITZM, ALVAREZ-GILAA,et al.Crop conditional convolutional neural networks for massive multi-crop plant disease classification over cell phone acquired images taken on real field conditions[J].Computers and Electronics in Agriculture,2019,167:105093.
[5]
FERENTINOSK P.Deep learning models for plant disease detection and diagnosis[J].Computers and Electronics in Agriculture,2018,145:311-318.
[6]
LIUB, ZHANGY, HED J,et al.Identification of apple leaf diseases based on deep convolutional neural networks[J].Symmetry,2017,10(1):11.
[7]
KHANM A, AKRAMT, SHARIFM,et al.CCDF:Automatic system for segmentation and recognition of fruit crops diseases based on correlation coefficient and deep CNN features[J].Computers and Electronics in Agriculture,2018,155:220-236.
RENS G, JIAF W, GUX J,et al.Recognition and segmentation model of tomato leaf diseases based on deconvolution-guiding[J].Transactions of the Chinese Society of Agricultural Engineering,2020,36(12):186-195.
LIUY, GAOG Q.Identification of multiple leaf diseases using improved SqueezeNet model[J].Transactions of the Chinese Society of Agricultural Engineering,2021,37(2):187-195.
[12]
BIC, WANGJ, DUANY,et al.MobileNet based apple leaf diseases identification[J].Mobile Networks and Applications,2020,27:172-180.
WANGM H, WUZ X, ZHOUZ G.Fine-grained identification research of crop pests and diseases based on improved CBAM via attention[J].Transactions of the Chinese Society for Agricultural Machinery,2021,52(4):239-247.
MAYILAR, MAMATS, NIGELAT,et al.The ecosystem service value spatial-temporal changes in the Ugan-kuqa River Delta Oasis based on RS and GIS[J].Acta Ecologica Sinica,2018,38(16):5938-5951.
HEJ H, WENG F, LIC X.Research on small sample defect detection based on optimized Faster R-CNN algorithm[J].Industrial Instrumentation & Automation,2024(5):94-101.
YINC C, ZHAOM, WANGX H,et al.A dataset of SEM images of atmospheric particles in Qingdao[J].China Scientific Data,2024,9(2):366-374.
[22]
吴树贤.基于深度学习的医学影像肿瘤分割算法研究[D].广州:广州大学,2024.
[23]
WUS X.Research on medical imaging tumor segmentation algorithm based on deep learning[D].Guangzhou:Guangzhou University,2024.
[24]
KRIZHEVSKYA, SUTSKEVERI, HINTONG E.ImageNet classification with deep convolutional neural networks[J].Communications of ACM,2017,60(6):84-90.
[25]
SIMONYANK, ZISSERMANA.Very deep convolutional networks for large-scale image recognition[J].arXiv preprint arXiv:2014.
[26]
HEK, ZHANGX, RENS,et al.Deep residual learning for image recognition[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas,NV,USA.IEEE,2016:770-778.
[27]
SANDLERM, HOWARDA, ZHUM,et al.Mobilenetv2:Inverted residuals and linear bottlenecks[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City,UT,USA.IEEE,2018:4510-4520.
[28]
WANGF, JIANGM, QIANC,et al.Residual attention network for image classification[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition.Hololulu,HI,USA,IEEE,2017:3156-3164.
[29]
HUJ, SHENL, SUNG.Squeeze-and-excitation networks[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Las Vegas,NV,USA.IEEE,2018:7132-7141.
[30]
WOO S, PARKJ, LEEJ Y,et al.CBAM:Convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision (ECCV).Munich,Germany.2018:3-19.
IOFFES, SZEGEDYC.Batch normalization:Accelerating deep network training by reducing internal covariate shift[C]//Proceedings of the 32nd International Conference on Machine Learning.Lille France.PMLR,2015:448-456.
[33]
SELVARAJUR R, COGSWELLM,DAS A,et al.Grad-CAM:Visual explanations from deep networks via gradient-based localization[C]//Proceedings of 2017 IEEE International Conference on Computer Vision.Venice,Italy.IEEE,2017:618-626.
[34]
WANGH, LONGH, WANGA,et al.Deep learning and regularization algorithms for malicious code classification[J].IEEE Access,2021,9:91512-91523.
[35]
LIUZ, LIJ, SHENZ,et al.Learning efficient convolutional networks through network slimming[C]//Proceedings of 2017 IEEE International Conference on Computer Vision.Venice,Italy.IEEE,2017:2736-2744.
[36]
SAINIR, JHAN K,DAS B,et al.ULSAM:Ultra-lightweight subspace attention module for compact convolutional neural networks[C]//Proceedings of 2020 IEEE Winter Conference on Applications of Computer Vision.Snowmass,CO,USA.IEEE,2020:1627-1636.
LIT T, WANGQ Q, TANGQ,et al.Study on the recognition of maize leaf disease based on deep learning with small sample size[J].New Generation of Information Technology,2023,6(24):1-5.