Naive Bayes Classifier in Grading Carabao Mangoes

Abstract

This study explores machine learning’s potential to classify carabao mangoes, a key Philippine export, into four grades based on size: A (large), B (medium), C (small), and R (reject). It introduces a Naïve Bayes classification model that uses image processing to extract features for grading. The goal is to create a consistent grading system to enhance export efficiency and benefit local farmers. The research aims to validate the Naïve Bayes model’s accuracy using size, weight, area, and spot ratio. It employs a quantitative, experimental design, manipulating image processing techniques to gauge their impact on classification accuracy. The results show the Naïve Bayes model achieved 95% accuracy, effectively distinguishing large and reject mangoes. It performed well for medium and small mangoes, with a 7% error rate between these classes. This indicates the model’s potential for quality control and sorting, though further refinement is needed to better differentiate between medium and small sizes. In conclusion, the study presents an image processing and Naïve Bayes-based method to classify carabao mangoes by size. The model’s high accuracy suggests its effectiveness and potential for automating mango classification, which could significantly aid the Philippine mango industry. Further performance assessment was conducted using a confusion matrix. The research highlights the promise of this approach for efficient mango grading.