Development of an algorithm to select bananas and quinces according to their state of maturity through artificial vision applied in the industry.

Abstract

The goal of this project is to create an algorithm that uses artificial vision to select bananas and quince in accordance with their maturity level. The usage of the Open CV and Numpy libraries, as well as the use of thresholding and binarization methods employing HSV in matrix format, are the specific goals. Python is the programming language used to create the classifier, and it is implemented in the WinPhython compiler that includes the Spyder interactive development environment (IDLE). On the other hand, OpenCV and Numpy libraries were employed, which offer particular mathematical and scientific capabilities for matrix operations. The algorithm could have been created with the help of the OpenCV and Numpy libraries, and as a result, it is also concluded that the degree of ripeness of the fruits could be detected by using artificial vision techniques like binarization, thresholding, and HSV in matrix format. The technique that was created made it possible to identify the fruit's level of quality in accordance with the limits of predetermined ranges. The algorithm's operational effectiveness was 98.6%.