基于改进CycleGAN的水稻叶片病害图像增强方法  

Rice Leaf Disease Image Enhancement Based on Improved CycleGAN

作　　者：严从宽 朱德泉[1] 孟凡凯 杨玉青 唐七星 张爱芳 廖娟 YAN Congkuan;ZHU Dequan;MENG Fankai;YANG Yuqing;TANG Qixing;ZHANG Aifang;LIAO Juan(School of Engineering,Anhui Agricultural University,Hefei 230036,China;Institute of Plant Protection and Agricultural Product Quality and Safety,Anhui Academy of Agricultural Sciences,Hefei 230031,China)

机构地区：[1]安徽农业大学工学院,安徽合肥230036 [2]安徽省农业科学院植物保护与农产品质量安全研究所,安徽合肥230031

出　　处：《智慧农业(中英文)》2024年第6期96-108,共13页Smart Agriculture

基　　金：国家重点研发计划项目子课题(2022YFD2001801-3);国家自然科学基金项目(32201665)。

摘　　要：[目的/意义]针对水稻病害图像识别任务存在数据集获取困难、样本不足及不同类别病害样本不均衡等问题,提出了一种基于改进CycleGAN(Cycle-Consistent Adversarial Networks)的水稻叶片病害图像数据增强方法。[方法]以CycleGAN为基本框架,将CBAM(Convolution Block Attention Module)注意力机制嵌入到生成器的残差模块中,增强CycleGAN对病害特征的提取能力,使网络更准确地捕捉小目标病害或域间差异不明显的特征;在损失函数中引入感知图像相似度损失,以指导模型在训练过程中生成高质量的样本图像,并提高模型训练的稳定性。基于生成的水稻病害样本,在不同目标检测模型上进行迁移训练,通过比较迁移学习前后模型性能的变化,验证生成的病害图像数据的有效性。[结果和讨论]改进的CycleGAN网络生成的水稻叶片病害图像质量优于原始Cy⁃cleGAN,病斑区域的视觉特征更加明显,结构相似性(Structural Similarity,SSIM)指标提升约3.15%,峰值信噪比(Peak Signal-to-Noise Ratio,PSNR)指标提升约8.19%。同时,使用YOLOv5s、YOLOv7-tiny和YOLOv8s这3种模型在生成的数据集上进行迁移学习后,模型的检测性能均有提升,如YOLOv5s模型的病害检测精度从79.7%提升至93.8%。[结论]本研究提出的方法有效解决了水稻病害图像数据集匮乏的问题,为水稻病害识别模型的训练提供了可靠的数据支撑。[Objective]Rice diseases significantly impact both the yield and quality of rice production.Automatic recognition of rice diseases using computer vision is crucial for ensuring high yields,quality,and efficiency.However,rice disease image recognition faces challenges such as limited availability of datasets,insufficient sample sizes,and imbalanced sample distributions across different disease categories.To address these challenges,a data augmentation method for rice leaf disease images was proposed based on an improved CycleGAN model in this reseach which aimed to expand disease image datasets by generating disease features,thereby alleviating the burden of collecting real disease data and providing more comprehensive and diverse data to support automatic rice disease recognition.[Methods]The proposed approach built upon the CycleGAN framework,with a key modification being the integration of a convolutional block attention module(CBAM)into the generator's residual module.This enhancement strengthened the network's ability to extract both local key features and global contextual information pertaining to rice disease-affected areas.The model increased its sensitivity to small-scale disease targets and subtle variations between healthy and diseased domains.This design effectively mitigated the potential loss of critical feature information during the image generation process,ensuring higher fidelity in the resulting images.Additionally,skip connections were introduced between the residual modules and the CBAM.These connections facilitate improved information flow between different layers of the network,addressing common issues such as gradient vanishing during the training of deep networks.Furthermore,a perception similarity loss function,designed to align with the human visual system,was incorporated into the overall loss function.This addition enabled the deep learning model to more accurately measure perceptual differences between the generated images and real images,thereby guiding the network towards producing

关 键 词：水稻叶片病害 数据增强 CycleGAN CBAM 感知相似度损失 迁移训练 

分 类 号：TP391[自动化与计算机技术—计算机应用技术] S43[自动化与计算机技术—计算机科学与技术]