A robust segmentation method combined with classification algorithms for field-based diagnosis of maize plant phytosanitary state

Abstract

Early diagnosis of maize-plant phytosanitary state in the field is crucial to prevent crop damage and optimize yield. However, this field diagnosis presents a challenge due to the variable background of the field environment, which can hinder the performance of classification algorithms. In this article, we introduced a novel segmentation technique using a combined normalized difference vegetation index that effectively isolates the features of interest, such as the leaves, from the surrounding image, which includes the diverse field background. To assess the effectiveness of our segmentation approach, we conducted early diagnosis of maize plants in the field using supervised classification algorithms. We generated a dataset that incorporated four essential texture features: energy, entropy, contrast, and inverse. These features were extracted from each of the segmented images using grayscale co-occurrence matrices. We employed four different classification methods, namely Adaboost, Random Forest, K-Nearest Neighbors, and support vector machine. When combined with the proposed segmentation technique, the support vector machine outperformed the other models, achieving an accuracy rate of 97%.

Keywords

• phytosanitary
• diagnosis
• maize
• segmentation
• adaboost
• random forest
• k-nearest neighbors
• support vector machine