Employing Deep Convolutional Neural Networks for Enhanced Precision in Potato and Maize Leaf Disease Detection and Classification

Turkish Journal of Engineering, Год журнала: 2025, Номер 9(2), С. 290 - 301

Опубликована: Янв. 18, 2025

Advances in image processing and techniques artificial intelligence have made it possible for computers to see learn. This article introduced a technology that has utilised MobilenetV2 Deep Convolution Neural Network architecture automatically identify diagnose plant diseases from images. The identification classification of are now carried out by only human experts-crop extension agents, farmers, expensive labour is prone mistakes. study relies on dataset gathering as technique classifying identifying diseases. It multistep process involving pre-process data the raw set, mask green area leaf, remove section, convert grayscale then obtain some characteristics, select, classify with regard disease management, etc. Two different types plants, maize potato, been taken consideration show effectiveness outcome proposed model. confusion matrix performance report were used evaluate system. potato comprised 6228 6878 images, respectively, leaves. Precise, recall, F1-scores 95.15%, 94.76%, 94.93% recorded cumulative across datasets respectively. translates its resistance picking most these crops, making resource can be confidence agriculture detection. MobileNetV2 model performs well both especially early blight common rust. Lower recognizing healthy leaves suggests feature space diseased may overlap. performed robust ability general detection affecting leaves, but specific areas need targeted further enhancement.

Язык: Английский

The selection and utilization of heading date loci in modern wheat breeding

New Crops, Год журнала: 2025, Номер unknown, С. 100066 - 100066

Опубликована: Янв. 1, 2025

Язык: Английский

Design Future Crops with Stress Resilience by CRISPR/Cas Reprogramming Noncoding RNAs

Опубликована: Май 9, 2025

Язык: Английский