Deep Learning-Based Convolutional Neural Network Approach for Smart Automated Classification and Sorting of Vegetables

The classification of vegetables plays a critical role in modern agriculture, food supply chains, and smart farming practices. Accurately identification of plants like vegetables apart is key for automating the classification, ensuring safe food and helping the environment. This project introduces a CNN type of model based on deep learning to aid in correctly classifying Bean, Bitter Guard, Bottle Guard, Brinjal, Broccoli, Cabbage, Capsicum, Carrot, Cauliflower and Cucumber. Twelve thousand images, each representing one class, were collected from Kaggle and organized into training, validation and testing subsets containing 70%, 20% and 10% of images, respectively. To make the CNN perform and generalize better, both dropout layers and max-pooling were used to improve the underlying structure. High accuracy of 99% was found in the experimental results and the precision, recall and F1-scores for all classes were consistently above 0.98. Loss and accuracy plots indicated that my model converged smoothly without strongly overfitting. Looking at the confusion matrix, we observed that the model performed well, because the main spots on the matrix were black and other spots were small and scattered. It backs the objectives of the Sustainable Development Goals by supporting food security, good health, advancements in industry, responsible purchases, infrastructure and actions against climate change through enhanced food processing and supply methods. This research confirms that the model can be used in automated vegetable sorting, development of agricultural technologies and smart food systems, boosting precision agriculture and digital security of food.

Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.