Development of a computer vision approach as a useful tool to assist producers in harvesting yellow melon in northeastern Brazil

• Published in: Computers and electronics in agriculture 2022-01, Vol.192, p.106554, Article 106554
• Main Authors: Ripardo Calixto, Renê, Pinheiro Neto, Luis Gonzaga, da Silveira Cavalcante, Tarique, Nascimento Lopes, Francisca Gleiciane, Ripardo de Alexandria, Auzuir, de Oliveira Silva, Ebenezer
• Format: Article
• Language: English
• Subjects: Brix value; Classification; Classifiers; Color; Computer Vision; Cucumis melo L; Digital cameras; Digital imaging; Harvesting; Image databases; K-Nearest Neighbor (KNN); Local Binary Pattern (LBP); Melons; Multi-Layer Perceptron (MLP); Nondestructive testing
• ISSN: 0168-1699; 1872-7107
• DOI: 10.1016/j.compag.2021.106554

•A simple and low-cost computer vision system to classify yellow melon at harvest time.•The method classifies yellow melon based on the soluble solids content (sweetness).•The method classifies in two classes: “suitable” or “unsuitable” for harvesting.•Melon growers anywhere may apply the model as it can be embedded in mobile devices.•The model has good sensitivity and specificity by Receiver Operation Characteristic. This paper presents a Computer Vision (CV) approach to harvest decision of yellow melon (hybrid Natal®) based on prediction of Soluble Solids Content (SSC, as °Brix) from digital image. At this point, it is worth remembering that the minimum SSC for harvesting this type of melon is 9°Brix. In this context, melons with SSC ≥ 9°Brix should be classified as “suitable for harvesting” (SFH), whereas melons with SCC