Hossain Md Arban, Sakib Saadman, Abdullah Hasan Muhammad, Arman Shifat E
Department of Robotics and Mechatronics Engineering, University of Dhaka, Dhaka 1000, Bangladesh.
GIS and Remote Sensing Lab, Department of Agroforestry and Environment, Bangabandhu Sheikh Mujibur Rahman Agricultural University, Gazipur 1706, Bangladesh.
Heliyon. 2024 Aug 22;10(17):e36361. doi: 10.1016/j.heliyon.2024.e36361. eCollection 2024 Sep 15.
Over the last decade, the use of machine learning in smart agriculture has surged in popularity. Deep learning, particularly Convolutional Neural Networks (CNNs), has been useful in identifying diseases in plants at an early stage. Recently, Vision Transformers (ViTs) have proven to be effective in image classification tasks. These architectures often outperform most state-of-the-art CNN models. However, the adoption of vision transformers in agriculture is still in its infancy. In this paper, we evaluated the performance of vision transformers in identification of mango leaf diseases and compare them with popular CNNs. We proposed an optimized model based on a pretrained Data-efficient Image Transformer (DeiT) architecture that achieves 99.75% accuracy, better than many popular CNNs including SqueezeNet, ShuffleNet, EfficientNet, DenseNet121, and MobileNet. We also demonstrated that vision transformers can have a shorter training time than CNNs, as they require fewer epochs to achieve optimal results. We also proposed a mobile app that uses the model as a backend to identify mango leaf diseases in real-time.
在过去十年中，机器学习在智能农业中的应用迅速普及。深度学习，尤其是卷积神经网络（CNN），在早期识别植物病害方面很有用。最近，视觉Transformer（ViT）已被证明在图像分类任务中很有效。这些架构通常优于大多数最先进的CNN模型。然而，视觉Transformer在农业中的应用仍处于起步阶段。在本文中，我们评估了视觉Transformer在识别芒果叶病害方面的性能，并将其与流行的CNN进行比较。我们基于预训练的数据高效图像Transformer（DeiT）架构提出了一种优化模型，该模型的准确率达到了99.75%，优于许多流行的CNN，包括SqueezeNet、ShuffleNet、EfficientNet、DenseNet121和MobileNet。我们还证明，视觉Transformer的训练时间可能比CNN短，因为它们需要更少的轮次就能达到最佳效果。我们还提出了一个移动应用程序，该应用程序使用该模型作为后端来实时识别芒果叶病害。
