Page 85 - IJAMD-2-2

International Journal of AI for
Materials and Design

ORIGINAL RESEARCH ARTICLE
Automated fruit sorting system integrating

image processing and support vector machine
techniques

Babatunde Olayinka Oyefeso 1 , Oluwaseun Emmanuel Oyewande 1 ,
and John Audu *
2
1 Department of Agricultural and Environmental Engineering, Faculty of Technology, University of
Ibadan, Ibadan, Oyo State, Nigeria
2 Department of Agricultural and Bio-systems Engineering, College of Engineering, Joseph Sarwuan
Tarka, University Makurdi, Benue State, Nigeria

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
*Corresponding author: in Python. Extracted features were then fed into a SVM model for the classification
John Audu process of fruits. The model demonstrated excellent performance, achieving an
(audu.john@uam.edu.ng)
accuracy of 100%, a precision of 96%, a recall of 92%, and an F1 score of 89%. The
Citation: Oyefeso BO, results indicated that incorporating multiple features significantly increases the
Oyewande OE, Audu J. Automated
fruit sorting system integrating accuracy of the classification. Moreover, the performance was optimized by selecting
image processing and support an appropriate regularization parameter during the training of the model and the use
vector machine techniques. Int J AI of polynomial kernel functions. Finally, the whole automated system was assembled
Mater Design. 2025;2(2):79-90.
doi: 10.36922/IJAMD025150011 to physically sort the classified fruits into different containers. This research highlights
the potential of integrating image processing and machine learning technologies
Received: April 8, 2025 to revolutionize fruit classification processes, thereby improving both efficiency and
1st revised: May 9, 2025 quality control in agriculture.
2nd revised: May 14, 2025
3rd revised: May 18, 2025 Keywords: Image processing; Fruit classification; Support vector machine; Automated
sorting; Feature extraction
Accepted: May 22, 2025
Published online: June 20, 2025
Copyright: © 2025 Author(s).
This is an Open-Access article 1. Introduction
distributed under the terms of the
Creative Commons Attribution Fruit image classification techniques are continually being developed due to their vital
License, permitting distribution, roles in agriculture and food analysis within the food industry. In the agricultural and
and reproduction in any medium, food industries, imaging technology streamlines operations by enhancing quality control
provided the original work is
properly cited. and optimizing the process. Mango production in Nigeria, the ninth most produced
fruit globally, is hindered by several challenges resulting from outdated technology. 1-9
Publisher’s Note: AccScience
Publishing remains neutral with It was reported in previous studies that the existing methods for manual classification
regard to jurisdictional claims in 10-13
published maps and institutional of fruits are somewhat inefficient, ineffective, slow, and prone to bias. Developments
affiliations. in image analysis have provided an efficient, reliable, and accurate system of fruit

Volume 2 Issue 2 (2025) 79 doi: 10.36922/IJAMD025150011