Aanis Ahmad

TL;DR: In this article, the authors compared the performance of three different pre-trained image classification models for classifying weed species and also assesses the accuracy of an object detection model for locating and identifying weed species.

TL;DR: In this article , the authors present a comprehensive overview of 70 studies on deep learning applications and the trends associated with their use for disease diagnosis and management in agriculture and provide a detailed assessment and considerations for developing deep learning-based tools for plant disease diagnosis in the form of seven key questions pertaining to (i) dataset requirements, availability, and usability, (ii) imaging sensors and data collection platforms, (iii) deep learning techniques, (iv) generalization of deep learning models, (v) disease severity estimation, (vi) DNN and human accuracy comparison, and (vii) open research topics.

TL;DR: In this article , a two-stage semantic segmentation approach was used to identify corn disease lesions and estimate their severity under complex field conditions, and the best performance for stage one was observed from the UNet model, which achieved up to 0.7379 and mBF score of 0.5351.

TL;DR: Details about four elements of a disease management system are presented and promising results for realizing a working system are provided.

TL;DR: In this article , a deep learning-based system for tracking diseased regions in corn fields was proposed. But, the system was only trained on images of tile sizes of 1000 × 1000 pixels and achieved a test accuracy of 100.00%.