Potato Plant Disease Detection from Leaf Images: A Study with Deep Transfer Learning and Features Fusion

Abstract

Monitoring of plant health based on the leaf images is a common practice in agriculture for effective disease detection and handling with preferred approach. In this work, potato leaf-image based disease analysis with deep-transfer-learning (DTL) is proposed with conventional and fused-features and the attained outcome is presented. This work considered the following stages to obtain better detection; leaf-data collection and resizing, feature extraction with DTL-model, feature based disease detection with SoftMax, features-fusion using 50% dropout, and classification with 3-foldc cross validation. This research considered 1200 images per class for analysis and performance is verified with individual-, and fused-features. This work considered the ResNet (RN) variants for the examination and the outcome of this work presents classification accuracy of >96% with Random-Forest (RF) classifier.

Plant phenotyping relevance

ジャガイモ葉画像から病害状態を推定する画像ベース手法を、深層転移学習・特徴抽出・特徴融合・分類・交差検証により中心的に開発・評価しているため。

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.