Scale-Invariant Feature Transformation and Meta-Ensemble Method for AI-Based Disease Detection in Agriculture

The turnip plant is an important agricultural product with high nutritional value. However, leaf diseases are a serious issue that reduces both yield and quality. Traditional diagnostic methods are time-consuming and prone to errors, which is why image processing and machine learning-based approaches are gaining increasing importance. This study proposes an advanced image processing method for the automatic detection of diseases in turnip leaves. First, powerful features are extracted from the leaf images using the Scale-Invariant Feature Transformation (SIFT) method. Then, these features are classified using a meta-ensemble model based on Linear Discriminant Analysis (LDA) and Support Vector Machines (SVM). The proposed method demonstrates a high performance with an accuracy rate of 99.28%. These results show that the developed model is a reliable and effective tool for the early diagnosis of plant diseases. The study contributes significantly to AI-based disease detection systems in agriculture.