基于改进ConvNeXt的苹果叶片病害分类算法

doi:10.16088/j.issn.1001-6600.2024072303

摘要/Abstract

摘要： 针对传统苹果叶片病害分类方法精准性差的问题,本文提出一种基于改进ConvNeXt的苹果叶片分类算法CALDNet (ConvNeXt apple leaf disease enhance network)。CALDNet设计3223结构的网络对模型结构进行调整,同时引入跳跃连接、位置编码以增强模型对空间的捕捉能力,提高训练过程中的稳定性;引入空间金字塔池化(spatial pyramid pooling, SPP)以捕捉不同尺度上的空间特征,增强模型对不同大小病斑的适应能力;在ConvNeXtblock的基础上,设计G-ConvNeXtblock,引入Gabor滤波器作为卷积核,对深度卷积进行改进,更好地捕捉图像中的纹理信息;为了提高模型对小范围苹果叶片病害的识别能力,设计一种增强型的通道和空间注意力机制(enhanced convolutional block attention module, enhanced CBAM)。实验以6种常见苹果叶片病害(黑星病、黑腐病、褐斑病、花叶病、锈病、灰斑病)及健康叶片为主要研究对象,并与主流算法进行对比。实验结果表明,CALDNet模型识别叶片病害的精确率、召回率以及F₁值达到97.58%、97.54%和97.54%,相较于原始ConvNeXt模型,分别提高4.63、4.56和4.60个百分点,参数量下降23.97%,解决了传统苹果叶片病害分类精准性差的问题。

关键词: 苹果叶片病害, ConvNeXt, CNN, 注意力机制, 深度学习

Abstract: Aiming at the problems of poor accuracy of traditional apple leaf disease classification methods, an apple leaf classification algorithm CALDNet based on improved ConvNeXt is proposed. 3223 Network is designed to adjust the structure of the model, while jump connection and position coding are introduced to enhance the model’s ability to capture the space and to improve the stability of the training process, and Spatial Pyramid Pooling (SPP) is used to capture spatial features on different scales and enhance the model’s ability to adapt to large and small lesions; on the basis of ConvNeXtblock, G-ConvNeXtblock is designed to improve the depth convolution, and a Gabor filter is introduced as a convolution kernel to better capture texture information in the image. In order to improve the model’s ability to recognize a small range of apple leaf disease recognition ability, an enhanced channel and attention mechanism (enhanced CBAM) is designed. In the experiments, seven common leaf diseases (black-star disease, black-rot, brown-spot, mosaic disease, healthy, rust, gray-spot) are chosed as the main research subjects, and the experimental results by using the improved algorithm and other mainstream algorithms are compared. The experimental results show that the CALDNet model recognizes the leaf disease model with the precision rate, recall rate, and F₁ value of 97.58%, 97.54%, and 97.54%, respectively, compared with the original ConvNeXt model, which increased by 4.63,4.56 and 4.60 percentage points, solving the problems of poor precision of traditional apple leaf disease classification.

Key words: apple leaf disease, ConvNeXt, CNN, attention mechanism, deep learning

中图分类号: TP391.41

石天怡, 南新元, 郭翔羽, 赵濮, 蔡鑫. 基于改进ConvNeXt的苹果叶片病害分类算法[J]. 广西师范大学学报（自然科学版）, 2025, 43(4): 83-96.

SHI Tianyi, NAN Xinyuan, GUO Xiangyu, ZHAO Pu, CAI Xin. Improved ConvNeXt-based Algorithm for Apple Leaf Disease Classification[J]. Journal of Guangxi Normal University(Natural Science Edition), 2025, 43(4): 83-96.

参考文献

[1] 胡清玉, 胡同乐, 王亚南, 等. 中国苹果病害发生与分布现状调查[J]. 植物保护, 2016,42(1): 175-179. DOI: 10.3969/j.issn.0529-1542.2016.01.032.
[2] 徐艳蕾, 孔朔琳, 陈清源, 等. 基于Transformer的强泛化苹果叶片病害识别模型[J]. 农业工程学报, 2022, 38(16): 198-206. DOI: 10.11975/j.issn.1002-6819.2022.16.022.
[3] 刘斌, 贾润昌, 朱先语, 等. 面向移动端的苹果叶部病虫害轻量级识别模型[J]. 农业工程学报, 2022, 38(6): 130-139. DOI: 10.11975/j.issn.1002-6819.2022.06.015.
[4] 姜红花, 杨祥海, 丁睿柔, 等. 基于改进ResNet18的苹果叶部病害多分类算法研究[J]. 农业机械学报, 2023, 54(4): 295-303. DOI: 10.6041/j.issn.1000-1298.2023.04.030.
[5] LV M, SU W H. YOLOV5-CBAM-C3TR: an optimized model based on transformer module and attention mechanism for apple leaf disease detection[J]. Frontiers in Plant Science, 2024, 14: 1323301. DOI: 10.3389/fpls.2023.1323301.
[6] CHEN X L, XING X Z, ZHANG Y Z, et al. MSCR-FuResNet: a three-residual network fusion model based on multi-scale feature extraction and enhanced channel spatial features for close-range apple leaf diseases classification under optimal conditions[J]. Horticulturae, 2024, 10(9): 953. DOI: 10.3390/horticulturae10090953.
[7] 李大湘, 曾小通, 刘颖. 耦合全局与局部特征的苹果叶部病害识别模型[J]. 农业工程学报, 2022, 38(16): 207-214. DOI: 10.11975/j.issn.1002-6819.2022.16.023.
[8] 鲍文霞, 吴刚, 胡根生, 等. 基于改进卷积神经网络的苹果叶部病害识别[J]. 安徽大学学报(自然科学版), 2021,45(1): 53-59. DOI: 10.3969/j.issn.1000-2162.2021.01.008.
[9] 于雪莹, 高继勇, 王首程, 等. 基于生成对抗网络和混合注意力机制残差网络的苹果病害识别[J]. 中国农机化学报, 2022,43(6): 166-174. DOI: 10.13733/j.jcam.issn.2095-5553.2022.06.022.
[10] LIU Z, MAO H Z, WU C Y, et al. A ConvNet for the 2020s[C]// 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Los Alamitos, CA: IEEE Computer Society, 2022: 11966-11976. DOI: 10.1109/CVPR52688.2022.01167.
[11] GAO Y X, CAO Z Z, CAI W W, et al. Apple leaf disease identification in complex background based on BAM-Net[J]. Agronomy, 2023, 13(5): 1240. DOI: 10.3390/agronomy13051240.
[12] LI X P, LI S Q. Transformer help CNN see better: a lightweight hybrid apple disease identification model based on transformers[J]. Agriculture, 2022, 12(6): 884. DOI: 10.3390/agriculture12060884.
[13] LU J W, LU B B, MA W L, et al. EAIS-Former: an efficient and accurate image segmentation method for fruit leaf diseases[J]. Computers and Electronics in Agriculture, 2024, 218: 108739. DOI: 10.1016/j.compag.2024.108739.
[14] 徐红明, 王兴华, 方诚, 等. 基于旋转不变性的高分辨率遥感影像船舶检测[J]. 中国航海, 2024,47(2): 120-127. DOI: 10.3969/j.issn.1000-4653.2024.02.016.
[15] WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[C]// Computer Vision-ECCV 2018. Cham: Springer International Publishing, 2018: 3-19. DOI: 10.1007/978-3-030-01234-2_1.
[16] YANG L X, ZHANG R Y, LI L D, et al. SimAM: a simple, parameter-free attention module for convolutional neural networks[J]. Proceedings of Machine Learning Research, 2021, 139: 11863-11874.
[17] HU J, SHEN L, ALBANIE S, et al. Squeeze-and-excitation networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020,42(8): 2011-2023. DOI: 10.1109/TPAMI.2019.2913372.
[18] HOU Q B, ZHOU D Q, FENG J S. Coordinate attention for efficient mobile network design[C]// 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Los Alamitos, CA: IEEE Computer Society, 2021: 13708-13717. DOI: 10.1109/CVPR46437.2021.01350.
[19] QIN Z Q, ZHANG P Y, WU F, et al. FcaNet: frequency channel attention networks[C]// 2021 IEEE/CVF International Conference on Computer Vision (ICCV). Los Alamitos, CA: IEEE Computer Society, 2021: 763-772. DOI: 10.1109/ICCV48922.2021.00082.
[20] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]// 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Los Alamitos, CA: IEEE Computer Society, 2016: 770-778. DOI: 10.1109/cvpr.2016.90.
[21] TAN M X, LE Q. EfficientNetV2: smaller models and faster training[J]. Proceedings of Machine Learning Research, 2021, 139: 10096-10106.
[22] IANDOLAF, MOSKEWICZ M, KARAYEV S, et al. DenseNet: implementing efficient ConvNet descriptor pyramids[EB/OL]. (2014-04-07)[2024-07-23]. https://doi.org/10.48550/arXiv.1404.1869. DOI: 10.48550/arXiv.1404.1869.
[23] WANG C Y, MARK LIAO H Y, WU Y H, et al. CSPNet: a new backbone that can enhance learning capability of CNN[C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Los Alamitos, CA: IEEE Computer Society, 2020: 1571-1580. DOI: 10.1109/CVPRW50498.2020.00203.
[24] XIE S N, GIRSHICK R, DOLLÁR P, et al. Aggregated residual transformations for deep neural networks[C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Los Alamitos, CA: IEEE Computer Society, 2017: 5987-5995. DOI: 10.1109/CVPR.2017.634.
[25] TROCKMAN A, KOLTER J Z. Patches are all you need?[EB/OL]. (2022-01-24)[2024-07-23]. https://arxiv.org/abs/2201.09792. DOI: 10.48550/arXiv.2201.09792.
[26] DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16x16 words: transformers for image recognition at scale[C]// International Conference on Learning Representations 2021. Red Hook: Curran Associates, Inc., 2021: 1-21.
[27] LIU Z, LIN Y T, CAO Y, et al. Swin transformer: hierarchical vision transformer using shifted windows[C]// 2021 IEEE/CVF International Conference on Computer Vision (ICCV). Los Alamitos, CA: IEEE Computer Society, 2021: 9992-10002. DOI: 10.1109/ICCV48922.2021.00986.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed