AI-Driven Nutritional Assessment Improving Diets with Machine Learning and Deep Learning for Food Image Classification

Maintaining a balanced and healthy diet is of utmost importance to prevent food-borne illnesses and promote overall well-being. To address this critical aspect of human health, we leverage the influence of deep learning algorithms and machine learning techniques to automate accurate food image classification and estimate essential food attributes. Our proposed approach entails the use of a sophisticated hybrid model that combines a deep learning convolutional neural network (CNN) and support vector machine (SVM), which efficiently categorizes various food items into specific groups of healthy and unhealthy classes. The proposed model streamlines the feature extraction process through CNN and harnesses the SVM classifier for classification tasks. To assess the efficacy of our approach, we conducted experiments utilizing a customized dataset. The experimental findings underline the exceptional performance of our hybrid model, achieving an impressive accuracy rate of 97%, which outperforms the standalone CNN model, yielding an accuracy of 94
^%
. Furthermore, our work demonstrates remarkable improvements across various metrics, including precision, f1-score, and recall.