Detection and Classification of Soybean Wilting Across Progressive Stages using Convolutional Neural Network Method

Abstract

Background: Food security being one of the prominent global issues requires strategies to maximize plant productivity with due consideration to sustainability. In this regard, precision agricultural practices are incorporated and are quite promising. The use of technology i.e. integrating AI is rapidly changing the complete agricultural scenario. A quick identification of wilting ensures farmers take early action and remedies. An early detection of plant wilting in a real-time scenario can avoid huge food crop losses but the whole task is humongous. The images collected from open fields over large areas can be analyzed via various image processing techniques. Using the CNN model for identification of early images for quick response to plant care saves the time and effort of the farmers. CNN utilization allows prompt wilting detection and early corrective action to protect the crop. In this paper, CNN trained on image data allows high predictability of wilting detection at early stages in Soybean plants. Methods: A well-defined dataset of 6704 pictures of soybean plants from agricultural fields is considered and allocated appropriately to train, test and validate the CNN model. Using image preprocessing, resizing and rescaling of images is done to ensure consistency of image dimensions. Noise elimination from the images is done via a low-pass filtering method to preserve low-frequency information and the images are converted to grayscale. Using standard Python libraries, data augmentation is ensured and 9158 images across all classes are arranged for the model. The performance evaluation matrix indicating accuracy percentage, precision percentage and recall percentage is estimated. Result: The proposed CNN algorithm is first calibrated using a set of images from the dataset and then tested for an entirely different set of images not used earlier. The overall accuracy is 91%. The model promises unambiguous identification of wilting in soybean leaves by appropriately classifying images set in 5 orders using a substantially ample dataset. Early identification in real time can prove to be of utmost benefit to the agricultural community in terms of eradication of the causes and yield retention of the crop.

Plant phenotyping relevance

CNNによる画像解析でダイズの萎凋状態を段階分類する手法を開発・検証しており、植物の病害・生理状態の取得が研究の中心である。

Code and data availability

The paper describes a 6704-image soybean wilting dataset and a VGG16-based CNN, but provides no public URL, repository, or identifier for the dataset, code, or trained model. The data availability statement only says the data is on 'Mendeley database site' without a link, and no authors' public URL appears in the text.

No evidence-backed public reproduction asset is currently recorded.