Nutricom: aplicación que recomienda alimentos saludables a partir de reconocimiento de alimentos en imágenes para evitar enfermedades

Abstract

The poor nutrition and feeding has become one of the great problems of modern life, causing a number of diseases and accelerating the transformation process. It is proposed to solve the problem with the implementation of a mobile application, based on artificial intelligence, which employs visual recognition of images suggested food intake or not, according to the user's profile including diseases, eating habits. The objective of the project was to classify the foods present in an image and calculate their caloric value to suggest healthy and nutritious foods. The methodology used was in cascade or life cycle, since it is the most common and oldest software development, and is widely used. The NUTRICOM mobile application can be integrated with the Watson API, visual recognition of food images, taking advantage of its ability to recognize more than 2,000 foods and "train" with it. Through the application, people can learn to eat well according to their profile. In conclusion, it can be said that for the visual image recognition API to have a correct operation, you must carry out a training or learning of at least 50 images per food