Lightweight CNN model improves plant disease identification accuracy

Researchers have developed a lightweight Multi-View Convolutional Neural Network designed for identifying plant diseases, aiming to overcome the computational intensity of traditional deep learning models. This new model utilizes additional features to enhance accuracy while requiring fewer parameters, making it more suitable for resource-constrained environments. Tested on the Plantvillage dataset, the proposed network achieved a 2.9% improvement in classification accuracy over a baseline RGB model and demonstrated comparable accuracy to state-of-the-art deep convolutional neural networks with reduced computational cost. AI

影响 Offers a more efficient approach to AI-driven agricultural diagnostics, potentially improving crop yields in resource-limited settings.

排序理由 This is a research paper detailing a new model architecture for a specific application. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

• arXiv
• Muhammad Kaleem Ullah Khan
• Plantvillage

• 论文
• 其他

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →