江苏农业学报2025，Vol.41Issue(5)：916-926,11.DOI:10.3969/j.issn.1000-4440.2025.05.010
基于改进DCGAN的棉叶螨为害图像数据增强方法
A data augmentation method for cotton leaf mite damage images based on improved DCGAN
摘要
Abstract
To address the insufficient and imbalanced sample sizes of cotton leaf mite damage images at different severity levels,reduce data collection costs,and enhance the quality and diversity of images generated by generative adversarial net-works,this study proposed an improved DCGAN-based data augmentation method for cotton leaf mite damage images.Based on the original model,category labels were introduced to enable targeted generation of images for different damage levels,effectively resolving the issue of class imbalance.The traditional direct connection structure was replaced with a residual structure to en-hance the model's ability to learn complex mapping relationships,avoid gradient vanishing problems,and improve the quality of generated images.Additionally,the convolutional block attention module(CBAM)was embedded in the convolutional layers to strengthen the model's capacity to extract key features of cotton leaf mite damage images,further enhancing the quality and diversity of generated images.Lastly,the Wasserstein distance with gradient penalty was employed as the loss func-tion,avoiding the problem of mode collapse and enhancing the training stability of the model.The improved DCGAN model outperformed the original model in terms of training stability and image quality.Its generated images achieved higher in-ception score(IS,8.51),fréchet inception distance(FID,150.12),kernel inception distance(KID,0.06),and structural simi-larity index measure(SSIM,0.82)than those generated by other classic data augmentation models.When training the DenseNet-121 model with the dataset generated by the improved DCGAN model,the average classification accuracy reached 88.02%,which was higher than that of DenseNet-121 models trained with datasets generated by traditional augmentation methods and other mod-els.This study provides technical support for intelligent monitoring of agricultural pests and diseases.关键词
棉叶螨/为害程度/深度卷积生成对抗网络(DCGAN)/图像数据增强Key words
cotton leaf mite/damage degree/deep convolutional generative adversarial network(DCGAN)/im-age data augmentation分类
信息技术与安全科学引用本文复制引用
雷竣杰,周保平..基于改进DCGAN的棉叶螨为害图像数据增强方法[J].江苏农业学报,2025,41(5):916-926,11.基金项目
国家自然科学基金项目(61563046) （61563046）
塔里木大学研究生科研创新项目(TDGRI202358) （TDGRI202358）
