Parez Sana, Dilshad Naqqash, Alghamdi Norah Saleh, Alanazi Turki M, Lee Jong Weon
Department of Software, Sejong University, Seoul 05006, Republic of Korea.
Department of Convergence Engineering for Intelligent Drone, Sejong University, Seoul 05006, Republic of Korea.
Sensors (Basel). 2023 Aug 4;23(15):6949. doi: 10.3390/s23156949.
In order for a country's economy to grow, agricultural development is essential. Plant diseases, however, severely hamper crop growth rate and quality. In the absence of domain experts and with low contrast information, accurate identification of these diseases is very challenging and time-consuming. This leads to an agricultural management system in need of a method for automatically detecting disease at an early stage. As a consequence of dimensionality reduction, CNN-based models use pooling layers, which results in the loss of vital information, including the precise location of the most prominent features. In response to these challenges, we propose a fine-tuned technique, , for detecting plant infections and diseases based on Vision Transformers (ViTs). Similar to word embedding, we divide the input image into smaller blocks or patches and feed these to the ViT sequentially. Our approach leverages the strengths of ViTs in order to overcome the problems associated with CNN-based models. Experiments on widely used benchmark datasets were conducted to evaluate the proposed performance. Based on the obtained experimental outcomes, the proposed technique outperforms state-of-the-art (SOTA) CNN models for detecting plant diseases.
为了使一个国家的经济增长，农业发展至关重要。然而，植物病害严重阻碍作物的生长速度和质量。在缺乏领域专家且信息对比度较低的情况下，准确识别这些病害极具挑战性且耗时。这导致农业管理系统需要一种能够在早期自动检测病害的方法。由于降维，基于卷积神经网络（CNN）的模型使用池化层，这会导致重要信息的丢失，包括最突出特征的精确位置。针对这些挑战，我们提出一种微调技术，用于基于视觉Transformer（ViT）检测植物感染和病害。与词嵌入类似，我们将输入图像划分为更小的块或补丁，并将它们依次输入到ViT中。我们的方法利用ViT的优势来克服与基于CNN的模型相关的问题。在广泛使用的基准数据集上进行了实验，以评估所提出方法的性能。基于获得的实验结果，所提出的技术在检测植物病害方面优于当前最先进的（SOTA）CNN模型。
