Home // MODERN SYSTEMS 2023, International Conference of Modern Systems Engineering Solutions // View article

Image Processing to Evaluate Post-harvest Damages on Grapes and Their Impact on Fruit Aspect

Authors:
Francisco Javier Diaz
Ali Ahmad
Lorena Parra
Sandra Sendra
Jaime Lloret

Keywords: Fungal disease; quality; image analysis techniques; Machine Learning; disease detection

Abstract:
The interaction between grapes and fungi is a topic that recently has increased its interest since it can benefit or reduce fruit quality. Multiple factors determine the quality of grapes, which is directly affected by their ripeness, flavour, colour and overall health. In the post-harvest process, decay due to water loss and fungal decay are major challenges in grape quality and preservation. In this paper, we aim to develop an image tool capable of spotting anomalies in the skin of grapes using image processing and machine learning. A series of cameras connected to nodes identify irregularities on grape skin. Pictures are processed, and the results are sent to a database where the feature extraction happens. Data is sent to the cloud, where machine learning classifies the state of the fruit. In order to perform our tests, 2 bunches of grapes were studied for 14 days. One bunch had their skin punctured, while the other was left untouched. The metrics selected to evaluate quality detection were accuracy and recall. According to the results, the modules that represent the most accuracy and recall are K-Nearest-Neighbor (KNN), followed by Artificial Neural Network (ANN). In the case of KNN, when 4 parameters are included, the accuracy reaches 100 %. Following this same pattern, the ANN module rose an accuracy of 95 % when 4 parameters were added. In addition, in the recall metric, KNN spiked at 95 % with the incorporation of 3 parameters, while ANN escalated to 90 % by adding 4 parameters.

Pages: 17 to 22

Copyright: Copyright (c) IARIA, 2023

Publication date: November 13, 2023

Published in: conference

ISBN: 978-1-68558-088-9

Location: Valencia, Spain

Dates: from November 13, 2023 to November 17, 2023