Quality assessment and prediction of Philippine mangoes: A convolutional neural network approach

• Main Authors: Cases, Carlos Matthew P., Rapliza, Annamitz A., Munsayac, Francisco Emmanuel T., Bugtai, Nilo T., Billiones, Robert Kerwin D., Baldovino, Renann G.
• Format: text
• Published: Animo Repository 2019
• Subjects: Mango—Grading—Automation; Neural networks (Computer science); Computer vision; Sorting devices; Manufacturing
• Online Access: https://animorepository.dlsu.edu.ph/faculty_research/2921
• Institution: De La Salle University

Philippines is one of the world's leading exporter of mangoes. The country produces many varieties of mangoes, one of which is the 'Carabao' mango. Several metric tons of mangoes are produced, and these have to be checked for defects before entering the market. With recent advances in technology, it has become efficient and relatively easy to use for these applications. The objective of this paper is to present a non-destructive method to check the quality of mangoes using computer vision (CV) and convolutional neural network (CNN) with a minimal number of samples. An experimental setup was created to simulate a production line. A webcam was used for capturing images of the mangoes, while a mini computer was used for controlling the peripherals. As basis for categorizing the mangoes as either good or bad, the Philippine National Standard (PNS) for mangoes was used. A basic background subtraction algorithm was used to extract the mango's image. With these extracted images, a 2-category network was trained, and the achieved classification accuracy was 97.21%. The goal of having a high accuracy in classifying mangoes was achieved. There are multiple paths to explore in the future, including additional feature extraction methods, different neural networks, and hardware improvements, in order to speed up the sorting process. Moreover, it may be necessary to be able to identify mangoes with only slight defects to be used for other products, such as dried mangoes, to reduce product wastage. © 2019 Insight Society.