Comparative analysis of convolutional neural network architectures for classification of plant leaf diseases

Abstract

Plants play an essential role in the life of any living organism, human or animal, so protecting this organism from disease is an urgent necessity for the survival of living organisms. The development of science has reduced the time required to discover a disease, allowing us to detect and treat diseases early using artificial intelligence. In this scientific paper, we compared the performance of (Vgg-16, MobileNet, and ConvNext) through time and accuracy among these models. We trained these models by using transfer learning models of convolutional neural networks (CNN) to classify plant diseases (potatoes, tomatoes, and peppers). We used a dataset containing 20,639 images divided into 15 classes of different diseases, we also used the same number of parameter and the same number of layers in vgg16 and mobilenet but in convnext 24 layers.The dataset from the Kaggle site and the work environment on google colab using Python language. The results are shown vgg-16 is a high accuracy of 0.97 during the training process from convnext and mobilenet,but MobilNet is faster in the time 62s.

Plant phenotyping relevance

植物葉画像から病害状態を分類するCNN手法を比較・評価しており、病害表現型の取得・推定が研究の中心である。

Code and data availability

公開本文の所在を確認できませんでした。非公開または購読が必要な可能性があります。

No evidence-backed public reproduction asset is currently recorded.