Influence of Illumination on Color based Potato Defect Detection

The global vegetable market demands rigorous quality analysis of potato crops to define their reasonable price. Highly accurate machine learning-based automated defect detection systems are necessary for this rising market. On the other hand, artificial illuminating lamps used in these learning decisive determining accuracy. Artificial should provide a perception color that is as similar possible natural color. This paper analysed skin measuring accuracy seven different illumination (L01 L07). ten samples with various defects, including one healthy potato. Experimental results proved lowest ΔE* was obtained when Compact Fluorescent lamp 45W, 6500 Correlated Color Temperature (CCT) (L1) an lamp. proposed experimental study will help develop methodologies future research by generating higher accuracies using L01-type