<![CDATA[Leaf area measurement is an important parameter in plant growth analysis because it is directly related to the photosynthesis process and biomass productivity. However, manual measurement methods are still destructive, time-consuming, and prone to errors due to variations in leaf morphology. This study aims to develop an actual leaf area measurement system based on Digital Image Processing using morphological operations that can work automatically, non-destructively, and in real-time. The research stages include image acquisition, preprocessing (grayscale and Gaussian blur), segmentation using the Otsu method, image enhancement with morphological operations, contour detection, and pixel-based area calculation converted to cm² units through a calibration process. Testing was carried out on 50 leaf samples consisting of perfect leaves, perforated leaves, and damaged leaves. The evaluation results showed an overall MAPE value of 22.20% with a system accuracy of 77.80%. The best performance was obtained in the perfect leaf category with an accuracy of 94.59%, followed by perforated leaves at 81.70%, while damaged leaves showed the lowest accuracy of 51.50%. These results indicate that the proposed method is effective on leaves with relatively intact shapes, but the level of accuracy is affected by morphological complexity and leaf contour irregularities]]>
Copyrights © 2026
