SM-CycleGAN: crop image data enhancement method based on self-attention mechanism CycleGAN

• Published in: Scientific reports Vol. 14; no. 1; p. 9277
• Main Authors: Liu, Dian, Cao, Yang, Yang, Jing, Wei, Jianyu, Zhang, Jili, Rao, Chenglin, Wu, Banghong, Zhang, Dabin
• Format: Journal Article
• Language: English
• Published: England Nature Publishing Group 23.04.2024; Nature Publishing Group UK; Nature Portfolio
• Subjects: Baking; Crop diseases; Crops; Cyclic consistency adversarial network; Disease detection; Disease recognition; PSNR; Self-attention mechanism; Signal-to-noise ratio; SSIM; Tea disease; Tobacco roasting; Tobacco roasting; PSNR; SSIM; Self-attention mechanism; Tea disease; Cyclic consistency adversarial network
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-024-59918-3

Crop disease detection and crop baking stage judgement require large image data to improve accuracy. However, the existing crop disease image datasets have high asymmetry, and the poor baking environment leads to image acquisition difficulties and colour distortion. Therefore, we explore the potential of the self-attention mechanism on crop image datasets and propose an innovative crop image data-enhancement method for recurrent generative adversarial networks (GANs) fused with the self-attention mechanism to significantly enhance the perception and information capture capabilities of recurrent GANs. By introducing the self-attention mechanism module, the cycle-consistent GAN (CycleGAN) is more adept at capturing the internal correlations and dependencies of image data, thus more effectively capturing the critical information among image data. Furthermore, we propose a new enhanced loss function for crop image data to optimise the model performance and meet specific task requirements. We further investigate crop image data enhancement in different contexts to validate the performance and stability of the model. The experimental results show that, the peak signal-to-noise ratio of the SM-CycleGAN for tobacco images and tea leaf disease images are improved by 2.13% and 3.55%, and the structural similarity index measure is improved by 1.16% and 2.48% compared to CycleGAN, respectively.