Tomato Sorting System Based on Type Using Deep Learning

Abstract

The tomato is a vegetable that is cultivated globally and plays a significant role in the culinary traditions of numerous countries. This vegetable needs to be separated after collection to meet the requirements of obtaining different flavors outside the growing season. This study focuses on the automatic separation of Rio tomatoes, which are preferred for tomato paste and sauces, from Fujimaru tomatoes using artificial intelligence and image processing techniques. Convolutional neural network (CNN), R-CNN, and Fast-CNN models were used to classify two different tomato types, and their performances were compared. According to the experimental results, it was observed that the CNN model achieved 94.1% accuracy, 93.5% precision, 94.7% recall, and 94.1% F1 score in the classification of Rio type tomatoes, and 92.4% accuracy, 91.8% precision, 93% recall, and 92.4% F1 score in the classification of Fujimaru type tomatoes. The hardware and software components used in the project are low cost, flexible, and modular. Experimental results show that the proposed model and system have high accuracy, precision, and efficiency rates.

Keywords

• deep learning
• convolution neural network (cnn)
• tomatto sorting
• derin öğrenme
• evrişimli sinir ağı
• domates ayırma