Pepper leaf disease recognition based on enhanced lightweight convolutional neural networks

Frontiers in Plant Science

Plant Science

Md Mehedi Hassan Dorjoy¹  Lixing Wang¹  Wenjing Sun¹  Min Dai¹  Shanwen Zhang¹  Hong Miao²  Xin Zhang³  Liangxiu Han³  Mingyou Wang⁴ 

[1] College of Mechanical Engineering, Yangzhou University, Yangzhou, China;College of Mechanical Engineering, Yangzhou University, Yangzhou, China;Nanjing Institute of Agricultural Mechanization, Ministry of Agriculture and Rural Affairs, Nanjing, China;Faculty of Science and Engineering, Manchester Metropolitan University Manchester, Manchester, United Kingdom;Nanjing Institute of Agricultural Mechanization, Ministry of Agriculture and Rural Affairs, Nanjing, China;

关键词: deep convolutional neural networks;    crop disease recognition;    GoogLeNet;    real-time recognition;    lightweight neural networks;   

DOI  :  10.3389/fpls.2023.1230886

 received in 2023-05-29, accepted in 2023-07-25,  发布年份 2023

来源: Frontiers

【 摘 要 】

Pepper leaf disease identification based on convolutional neural networks (CNNs) is one of the interesting research areas. However, most existing CNN-based pepper leaf disease detection models are suboptimal in terms of accuracy and computing performance. In particular, it is challenging to apply CNNs on embedded portable devices due to a large amount of computation and memory consumption for leaf disease recognition in large fields. Therefore, this paper introduces an enhanced lightweight model based on GoogLeNet architecture. The initial step involves compressing the Inception structure to reduce model parameters, leading to a remarkable enhancement in recognition speed. Furthermore, the network incorporates the spatial pyramid pooling structure to seamlessly integrate local and global features. Subsequently, the proposed improved model has been trained on the real dataset of 9183 images, containing 6 types of pepper diseases. The cross-validation results show that the model accuracy is 97.87%, which is 6% higher than that of GoogLeNet based on Inception-V1 and Inception-V3. The memory requirement of the model is only 10.3 MB, which is reduced by 52.31%-86.69%, comparing to GoogLeNet. We have also compared the model with the existing CNN-based models including AlexNet, ResNet-50 and MobileNet-V2. The result shows that the average inference time of the proposed model decreases by 61.49%, 41.78% and 23.81%, respectively. The results show that the proposed enhanced model can significantly improve performance in terms of accuracy and computing efficiency, which has potential to improve productivity in the pepper farming industry.

【 授权许可】

Unknown   
Copyright © 2023 Dai, Sun, Wang, Dorjoy, Zhang, Miao, Han, Zhang and Wang