Comparison Analysis of Machine Learning Classification on Apple Fruit Quality

Abstract This study presents a comparative analysis of classical and deep learning approaches for the classification of apple fruit quality, within the broader context of machine vision applications. Emphasizing the importance of the fruit's physical appearance in meeting market standards, the research explores the performance of classical methods such as Support Vector Machine (SVM), K-nearest neighbour (KNN), and Decision Tree (DT), in comparison to deep learning methods like Mobile-Net and Convolutional Neural Network (CNN) with self-design. A self-created dataset comprising 150 apple fruit images categorized into fresh, mid, and rotten classes are utilized, with an 80:20 training-test split. The evaluation of the approaches reveals promising results, with SVM achieving 86% accuracy, DT achieving 93%, KNN achieving 96.6%, and Mobile-Net and CNN achieving 97% accuracy. Notably, the study demonstrates the efficiency of these methods in classifying different quality classes of apple fruit. This research contributes to the existing knowledge in agricultural quality control and provides insights for researchers seeking suitable algorithms in the field of machine vision for fruit quality assessment, ultimately advancing the application of machine vision techniques in real-world scenarios.