FRUIT RIPENESS BASED ON RGB, HSV, HSL, L*a*b* COLOR FEATURE USING SVM
Jasman Pardede , Milda Gustiana Husada, Asep Nana Hermana, Sri Agustina Rumapea
In this study, we have generated a fruit ripeness dataset for 8 categories, viz. Ripe Mango, Ripe Tomato, Ripe Orange, Ripe Apple, Unripe Mango, Unripe Tomato, Unripe Orange, and Unripe Apple. Based on the fruit ripeness dataset we implemented the SVM algorithm. Color feature extraction implemented in this study are RGB, HSV, HSL, and L * a * b *.Based on experiment result, We have found that the best SVM model in determining fruit ripeness is the 6th degree polynomial kernel and by extracting HSV color features. We evaluated the model that we generate based on the value of accuracy, precision, recall, and F-Measure. The performance of our system for accuracy, precision, recall, the best F-Measures are0.76, 0.80, 0.76, and 0.78, respectively.
Keywords: fruit ripeness, SVM, color feature, HSV, performance