Citation: Hosainpour, A.; Kheiralipour, K.; Nadimi, M.; Paliwal, J. Quality Assessment of Dried White Mulberry (Morus alba L.) Using Machine Vision. Horticulturae 2022, 8, 1011. https://doi.org/10.3390/ horticulturae8111011 Academic Editor: Esmaeil Fallahi Received: 27 September 2022 Accepted: 27 October 2022 Published: 1 November 2022 Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affil- iations. Copyright: © 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https:// creativecommons.org/licenses/by/ 4.0/). horticulturae Article Quality Assessment of Dried White Mulberry (Morus alba L.) Using Machine Vision Adel Hosainpour 1, *, Kamran Kheiralipour 2 , Mohammad Nadimi 3 and Jitendra Paliwal 3 1 Mechanical Engineering of Biosystems Department, Urmia University, Urmia 5756151818, Iran 2 Mechanical Engineering of Biosystems Department, Ilam University, Ilam 6939177111, Iran 3 Department of Biosystems Engineering, University of Manitoba, Winnipeg, MB R3T 5V6, Canada * Correspondence: a.hosainpour@urmia.ac.ir; Tel./Fax: +98-4432775035 Abstract: Over the past decade, the fresh white mulberry (Morus alba L.) fruit has gained growing interest due to its superior health and nutritional characteristics. While white mulberry is consumed as fresh fruit in several countries, it is also popular in dried form as a healthy snack food. One of the main challenges that have prevented a wider consumer uptake of this nutritious fruit is the non-uniformity in its quality grading. Therefore, identifying a reliable quality grading tool can greatly benefit the relevant stakeholders. The present research addresses this need by developing a novel machine vision system that combines the key strengths of image processing and artificial intelligence. Two grades (i.e., high- and low-quality) of white mulberry were imaged using a digital camera and 285 colour and textural features were extracted from their RGB images. Using the quadratic sequential feature selection method, a subset of 23 optimum features was identified to classify samples into two grades using artificial neural networks (ANN) and support vector machine (SVM) classifiers. The developed system under both classifiers achieved the highest correct classification rate (CCR) of 100%. Indeed, the latter approach offered a smaller mean squared error for the training and test sets. The developed model’s high accuracy confirms the machine vision’s suitability as a reliable, low-cost, rapid, and intelligent tool for quality monitoring of dried white mulberry. Keywords: dried mulberry; quality grading; image processing; feature classification; artificial neural networks 1. Introduction With an increasing demand for healthy and nutritious agri-food products, berries have gained a lot of interest around the globe. For instance, the global import value of fresh mulberries, raspberries, loganberries, and blackberries has risen from USD 1.7 billion in 2014 to USD 3.8 billion in 2021. The top five importers of berries above include the United States, Germany, Canada, United Kingdom, and Spain, with 43%, 10%, 9%, 9%, and 6% of the global market import, respectively [1]. Among berry fruits, white mulberry is of great interest as it contains carbohydrates, protein, fiber, fat, vitamins and minerals [2,3]. Moreover, the phenolic compounds of white mulberry have a wide range of antioxidant and antimutagenic activities and anti-cancer properties [3–5]. White mulberry can be consumed both in fresh or dried form (as a healthy snack food) [4]. However, the main challenge the industry is facing in trading this nutritious fruit, specifically in its dried form, is the inconsistency in its quality grading due to a lack of well-developed tools. The quality of the fresh fruit and the drying conditions are the main factors that determine the dried white mulberry quality. High-quality products usually have negligible damaged/broken components and are milky in colour. In contrast, lower-quality dried samples have several damaged/broken/smashed pieces and are darker in colour. The industry’s common approach for grading dried mulberry is a visual inspection conducted Horticulturae 2022, 8, 1011. https://doi.org/10.3390/horticulturae8111011 https://www.mdpi.com/journal/horticulturae