Oil packaging design using Artificial Intelligence techniques

Abstract

Since beginning design, the designer has used his hands, wits, and pencil to transform an idea into a functional product that serves its purpose. With advances in Deep Learning and convolutional neural networks, a new tool has emerged: generative models of images from text. With the purpose of testing, evaluating and directing these models to apply them to the design of new products, we have focused on a specific product field, olive oil containers, a fairly broad and perfect field for the use of these models, as they are only capable of generating an image; they cannot provide measurement values or volumes of the object. Therefore, oil containers are a perfect starting point: everyday products whose shapes and aesthetics vary by brand and desired shape. The aim is to use these new tools and give them their place of application in the conceptual product design process in the state-of-the-art field of product development. In this work, we will examine the models available on the market and the techniques that can guide them. We will evaluate the results from different image evaluation methods generated by artificial intelligence and the assessments obtained, to propose a methodology and a model for the execution of new conceptual designs.