Grading of Carica Papaya Using Image Processing and Support Vector Machine on Raspberry PI

This research applied the concept of image processing and machine learning to grade the quality of Carica Papaya images based on the Philippine National Standards. The main objective was to develop a system that graded the fruit using a Support Vector Machine, K-means Clustering, and Gray-Level Co-occurrence Matrix. K-means was used to extract the color of the fruit, while the Gray-Level Co-occurrence Matrix used textural features: Dissimilarity, Homogeneity, Contrast, Angular Second Moment (ASM), and Energy to calculate the textures of the fruit. The obtained results showed that the majority of the samples were correctly classified. The overall accuracy of the system was 81.67%. Therefore, it was concluded that using these methods, the system could correctly grade the quality of Carica Papaya based on the Philippine National Standards, categorizing them into extra class, class 1, and class 2. While the unknown category was included to label cases beyond the scope of the study.