A Novel Approach for Automated Strawberry Fruit Varieties Classification Using Image Processing and Machine Learning

Strawberry fruit classification is a crucial step in the strawberry farming industry, as it contributes to quality control and optimization of harvest. However, manual classification is often error-prone and inefficient. In this study, a new method of strawberry fruit classification based on machine learning was proposed using a combination of image processing techniques. The proposed approach includes the pre-processing of the images of four groups of strawberries (Queen Elisa, Paros, Ventana, and Kurdistan), followed by the recognition and classification of their fruit varieties. For this purpose, fruit shape characteristics were extracted and entered into the machine learning models for classification. Two different machine learning algorithms, namely artificial neural networks (ANN) and support vector machine (SVM), were evaluated for their performance in fruit classification. The results of the efficiency of the proposed approach in the classification of strawberry fruits were 97.5 and $92.5 \%$, respectively. The proposed method is scalable, robust, and efficient, making it suitable for use in commercial strawberry farming operations.