Image Segmentation Analysis Using Otsu Thresholding and Mean Denoising for the Identification Coffee Plant Diseases

Abstract

In Indonesia, coffee is one of the plantation products with a relatively high level of productivity and is a source of foreign exchange income for the country. However, unfortunately, certain factors can threaten productivity and quality in cultivating coffee plants, one of which is rust leaf disease. This disease causes disturbances in photosynthesis, thereby reducing plant yields. Therefore, to maintain and control productivity in coffee cultivation, this research carried out the process of observing coffee leaf images through segmentation using the Otsu Thresholding and Mean Denoising methods. The entire series of processes in this research was carried out using the Python programming language and succeeded in providing output in the form of image comparisons showing areas affected by Rust Leaf disease using the Otsu thresholding method alone and the Otsu thresholding method combined with a non-local means denoising algorithm. The test results prove that the Otsu thresholding method with the non-local means denoising algorithm has a smaller MSE value. It is the most optimal method for handling coffee leaf disease image segmentation with an accuracy level of 88%. It is hoped that this research can support farmers in providing insight into early detection of coffee plant diseases and increasing productivity through visual analysis.

Plant phenotyping relevance

コーヒー葉の病斑領域を画像セグメンテーションで抽出し、植物の病害状態を推定する手法の開発・比較が中心であるため。

Code and data availability

The paper uses a public Kaggle coffee-leaf image dataset and Python code, but provides no authors' public URL, repository link, or deposit statement for the code or the specific dataset subset; no qualifying paper-specific public asset is identified.

No evidence-backed public reproduction asset is currently recorded.