A Classification Algorithm for Date Fruits
Adnan Ahmed Abi Sen, Nour Mahmoud Bahbouh, Ahmad B. Alkhodre, Ashwaq Mohammed Aldhawi, Fatmah Ahmad Aldham, Manar Aljabri
Abstract
Date fruits are very popular in Saudi Arabia and around the world. Date fruits have several sizes, colors, taste and value. There are a lot of challenges facing the date industry. One of the most significant challenges is the classification and sorting of dates without any physical measurement. This research presents comparison among many automatic classification algorithms with six proposed features mainly relying on (color, size, and texture). The dataset contains images of four main types of dates in Saudi Arabia. The results from testing proved the viability of the selected features of dates according to different metrics of accuracy, in addition to the confusion matrix. Also, the results showed that the Support Vector Machine model has overcome others (Neural Network, Decision Tree, and Random Forest models), bearing in mind that the used dataset was small. The accuracy of the Vector Machine was 0.738, while others were between 0.6 and 0.69. These percentages would be enhanced in the real environment, if the same camera and same conditions are available.