An Effective Image-Based Tomato Leaf Disease Segmentation Method Using MC-UNet

Yubao Deng; Haoran Xi; Guoxiong Zhou; Aibin Chen; Yanfeng Wang; Liujun Li; Yahui Hu

doi:10.34133/plantphenomics.0049

An Effective Image-Based Tomato Leaf Disease Segmentation Method Using MC-UNet

Plant Phenomics. 2023 May 15:5:0049. doi: 10.34133/plantphenomics.0049. eCollection 2023.

Authors

Yubao Deng¹, Haoran Xi², Guoxiong Zhou¹, Aibin Chen¹, Yanfeng Wang³, Liujun Li⁴, Yahui Hu⁵

Affiliations

¹ College of Computer & Information Engineering, Central South University of Forestry and Technology, Changsha, 410004, Hunan, China.
² College of Mechanical & Electrical Engineering, Central South University of Forestry and Technology, Changsha, 410004, Hunan, China.
³ National University of Defense Technology, 410015, Changsha, Hunan, China.
⁴ Department of Soil and Water Systems, University of Idaho, Moscow, ID, 83844, USA.
⁵ Plant Protection Research Institute, Academy of Agricultural Sciences, 410125, Changsha, Hunan, China.

Abstract

Tomato disease control is an urgent requirement in the field of intellectual agriculture, and one of the keys to it is quantitative identification and precise segmentation of tomato leaf diseases. Some diseased areas on tomato leaves are tiny and may go unnoticed during segmentation. Blurred edge also makes the segmentation accuracy poor. Based on UNet, we propose an effective image-based tomato leaf disease segmentation method called Cross-layer Attention Fusion Mechanism combined with Multi-scale Convolution Module (MC-UNet). First, a Multi-scale Convolution Module is proposed. This module obtains multiscale information about tomato disease by employing 3 convolution kernels of different sizes, and it highlights the edge feature information of tomato disease using the Squeeze-and-Excitation Module. Second, a Cross-layer Attention Fusion Mechanism is proposed. This mechanism highlights tomato leaf disease locations via gating structure and fusion operation. Then, we employ SoftPool rather than MaxPool to retain valid information on tomato leaves. Finally, we use the SeLU function appropriately to avoid network neuron dropout. We compared MC-UNet to the existing segmentation network on our self-built tomato leaf disease segmentation dataset and MC-UNet achieved 91.32% accuracy and 6.67M parameters. Our method achieves good results for tomato leaf disease segmentation, which demonstrates the effectiveness of the proposed methods.