GrapeGAN: Unsupervised image enhancement for improved grape leaf disease recognition

Haibin Jin,Yue Li,Jianfang Qi,Jianying Feng,Dong Tian,Weisong Mu

Computers and Electronics in Agriculture（2022）

引用 15|浏览7

暂无评分

摘要

•A novel method for data enhancement of grape leaf disease images is proposed.•The proposed method relies on feature fusion mechanism and capsule structure.•GrapeGAN generates high quality images with full structure and a FID of 5.495.•The recognition accuracy of images generated by the GrapeGAN can reach 96.13%.

查看译文

关键词

Grape disease identification,Data augmentation,Generative adversarial networks,Convolutional neural networks

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要