Automated fruit sorting system integrating image processing and support vector machine techniques

Abstract

Traditional fruit grading methods are mostly time-consuming and subjective, thereby limiting efficiency in the agricultural sector. To address these problems, this paper presents the design and implementation of an automated fruit sorting system for classifying certain fruits, namely oranges, tomatoes, and mangoes, using image processing and support vector machine (SVM) techniques. An ESP32 camera was used to capture images of the fruits, which were later passed through algorithms in Python. Extracted features were then fed into a SVM model for the classification process of fruits. The model demonstrated excellent performance, achieving an accuracy of 100%, a precision of 96%, a recall of 92%, and an F1 score of 89%. The results indicated that incorporating multiple features significantly increases the accuracy of the classification. Moreover, the performance was optimized by selecting an appropriate regularization parameter during the training of the model and the use of polynomial kernel functions. Finally, the whole automated system was assembled to physically sort the classified fruits into different containers. This research highlights the potential of integrating image processing and machine learning technologies to revolutionize fruit classification processes, thereby improving both efficiency and quality control in agriculture.