Research Article | Open Access

Volume 2024 |Article ID 0218 | https://doi.org/10.34133/plantphenomics.0218

AISOA-SSformer: An Effective Image Segmentation Method for Rice Leaf Disease Based on the Transformer Architecture

Weisi Dai,¹ Wenke Zhu,² Guoxiong Zhou ,¹ Genhua Liu ,¹ Jiaxin Xu,¹ Hongliang Zhou,¹ Yahui Hu,³ Zewei Liu,¹ Jinyang Li,¹ and Liujun Li⁴

¹Faculty of Electronic Information and Physics, Central South University of Forestry and Technology,Changsha, 410004 Hunan, China
²College of Bangor, Central South University of Forestry andTechnology, Changsha, 410004 Hunan, China
³Plant Protection Institute, Hunan Academy of AgriculturalSciences, Changsha, 410125 Hunan, China
⁴Department of Soil and Water Systems, University of Idaho,Moscow, ID 83844, USA

Abstract

Rice leaf diseases have an important impact on modern farming, threatening crop health and yield. Accurate semantic segmentation techniques are crucial for segmenting diseased leaf parts and assisting farmers in disease identification. However, the diversity of rice growing environments and the complexity of leaf diseases pose challenges. To address these issues, this study introduces an innovative semantic segmentation algorithm for rice leaf pests and diseases based on the Transformer architecture AISOA-SSformer. First, it features the sparse global-update perceptron for real-time parameter updating, enhancing model stability and accuracy in learning irregular leaf features. Second, the salient feature attention mechanism is introduced to separate and reorganize features using the spatial reconstruction module (SRM) and channel reconstruction module (CRM), focusing on salient feature extraction and reducing background interference. Additionally, the annealing-integrated sparrow optimization algorithm fine-tunes the sparrow algorithm, gradually reducing the stochastic search amplitude to minimize loss. This enhances the model’s adaptability and robustness, particularly against fuzzy edge features. The experimental results show that AISOA-SSformer achieves an 83.1% MIoU, an 80.3% Dice coefficient, and a 76.5% recall on a homemade dataset, with a model size of only 14.71 million parameters. Compared with other popular algorithms, it demonstrates greater accuracy in rice leaf disease segmentation. This method effectively improves segmentation, providing valuable insights for modern plantation management. The data and code used in this study will be open sourced at https://github.com/ZhouGuoXiong/Rice-Leaf-Disease-Segmentation-Dataset-Code.