Identification and Detection of Sugarcane Crop Disease Using Image Processing

Abstract

Sugarcane is a renewable, natural agriculture resource and it is most important crop of India. Sugarcane Crop is a perennial crop which results into less labour and high yields. Sugarcane crop is one of the main pillar for Indian economy. Nowadays there are different diseases which affecting the sugarcane plants in diverse areas. So In this work we are going to use machine learning algorithms and image processing for sugarcane leaf disease detection. Machine learning is a trending area where the technological benefits can be imparted to the agriculture field also. In this we are going to use PCA algorithm which is one of the unsupervised machine learning algorithms. The dataset consists of 3 types of diseases. Total dataset is divided into various proportions of training and testing sets. There are various detection and classification techniques which are done using various algorithms at each stage but in PCA algorithm detection and classification is done by same algorithm which is PCA. The diseases of sugarcane consider in this project are red rot, smut, wilt.

Plant phenotyping relevance

サトウキビ葉の画像から病害状態を検出・分類する画像処理と機械学習が研究の中心であり、植物の病害表現型を直接推定している。

Code and data availability

The paper describes a MATLAB PCA-based sugarcane leaf disease detection system with a self-collected image dataset, but provides no public dataset, code, model, or supplement availability statement or URL. No paper-specific public asset is identifiable.

No evidence-backed public reproduction asset is currently recorded.