This research aims to develop an image
processing method for monitoring and evaluating the
quality changes in vegetables using image texture analysis, with lettuce as the sample. Thirty grams of lettuce were prepared by washing, trimming, and centrifuging in a salad spinner for 1 minute to remove excess water. The prepared lettuce samples were then packaged in LDPE bags and stored at different temperatures (4°C, 7°C, and 10°C, respectively). Images of the lettuce samples were captured every 24 hours for 8 days under D65 light at a resolution of 3024 × 4032 pixels. The images were saved in RGB format, converted to HSI color space, and the H (Hue angle) value was used to calculate image texture features using statistical calculation techniques, including Energy, Entropy, Correlation, and Homogeneity. The results of the study indicated that the Energy value could effectively monitor the rate of change in lettuce quality over time based on shelf life and storage temperature. The Energy value exhibited a significant decrease depending on the shelf life and storage temperature, with the decrease being statistically significant (P < 0.05) and proportional to the storage temperature. In contrast, Entropy, Correlation, and Homogeneity values were found to be ineffective
for monitoring the rate of change in lettuce quality.