NUTRIENT COMPOSITION PREDICTION IN FOOD PRODUCTS USING IMAGE PROCESSING AND AI TECHNIQUES
Abstract
Accurate prediction of nutrient composition in food products is essential for enhancing dietary recommendations and ensuring food safety. Traditional methods for nutrient analysis are time-consuming and often require expensive laboratory equipment. In response to these limitations, recent advances in image processing and artificial intelligence (AI) offer promising alternatives for predicting the nutrient composition of food products. This study proposes a novel approach that integrates image processing techniques with AI algorithms to analyze visual data from food products and predict their nutrient content, including macronutrients like proteins, fats, and carbohydrates, as well as micronutrients such as vitamins and minerals. High-resolution images of various food items are captured and pre-processed using advanced image processing techniques to enhance relevant features, such as texture, color, and shape. These features are then fed into a deep learning model, specifically a Convolutional Neural Network (CNN), designed to extract patterns and correlations between visual characteristics and nutrient composition. The model is trained on a comprehensive dataset of labeled food images, which includes nutrient information obtained through traditional laboratory analysis. To evaluate the accuracy and robustness of the proposed method, the predicted nutrient compositions are compared against actual values from laboratory tests. The results demonstrate that the AI-based model achieves high accuracy, with predictions closely matching laboratory findings. This approach significantly reduces the time and cost associated with nutrient analysis while maintaining a high level of precision. The findings of this study suggest that image processing combined with AI techniques offers a viable and efficient solution for nutrient composition prediction in food products, paving the way for its application in the food industry, personalized nutrition, and public health monitoring.
