<![CDATA[The decline in grape (Vitis vinifera) productivity is often caused by leaf diseases such as Black Rot, which are challenging to detect accurately through manual visual inspection The key point of this research is to compare the performance of two Machine Learning classification algorithms, namely Support Vector Machine (SVM) and Random Forest, to identify the most optimal model for disease detection. The methodology employs digital image processing with Histogram Color (HSV) feature extraction, which is chosen for its efficiency in representing color changes caused by infection. The grape leaf disease image dataset was classified and evaluated. The comparative results demonstrate that Random Forest achieved the highest accuracy of 95.32%, slightly surpassing SVM which reached 94.48%. These findings prove that both algorithms perform excellently, but Random Forest is more recommended for this dataset due to its superior robustness in accurately predicting disease classes.]]>
Copyrights © 2026
