Automated Fruit Classification Using KNN and Decision Trees for Enhanced Agricultural Efficiency and Accuracy

Industrial and agricultural use requires fruit colour, size, shape, and texture classification. Classification enhances sorting, grading, quality control, and customer satisfaction. Autoclassification is rapid and accurate, while manual classification is slow and erroneous. Premium food demand is rising. This paper proposes using KNN and DT algorithms for automated fruit classification to improve efficiency and accuracy. Kaggle provided 490 training and 166 test pineapple and coco photos. Data visualization, principal component analysis, and binary classification with KNN and DT classifiers were used. DT was 86.45% accurate, much behind KNN's 96.99%. This study found that KNN and DT algorithms improve fruit categorization accuracy and efficiency, lowering post-harvest losses, preserving product standards, and improving agricultural supply chain stakeholder decision-making. Better agricultural technology, precision agriculture, integrated systems, and sustainable practices will benefit producers and consumers.