Date fruits are considered as one of the most popular fruits in the Middle East. Oman is one of the countries that have many varieties of dates and the most well-known are Khalas, Fardh and Khunaizi. Nowadays, the process of classifying different varieties of dates in date’s industries is done manually by human workers. The manual process affects the quality of dates, which however is subjective, time consuming, laborious and expensive. The objective of this paper is to classify automatically six popular date varieties, namely, Khalas, Khunaizi, Fardh, Qash, Naghal, and Maan from their images based on color, shape, size, and texture features. Three different artificial intelligence techniques have been used for automatic classification and qualitative comparison; (i) Artificial Neural Network (ANN), (ii) Support Vector Machine (SVM), and (iii) KNearest Neighbor (KNN). The Dates’ varieties were obtained from AL-Dhahira Governorate. In total, 600 date samples (100 dates/class) were selected. These samples were imaged individually, one date per image. Nineteen features were extracted from each image and used in classification models. Experimental results show that the ANN algorithm outperforms the SVM and KNN based algorithms in all criteria used. The achieved results of ANN using 15 features and seven tan-sigmoid neurons in the hidden layer were 99.2% in classification accuracy, 99.12% in average recall and 99.25% in average precision.