Generative AI: Proposal and Pilot Study ofa Method for Generating Average Aquagram Images Based on Skin Data Characteristics UsingGPT o4 and Artbreeder within the Framework of Aquaphotomics Theory

In recent years, research has been active in various fields to measure and collect spectrum data on the moisture content of a wide variety of plants and animals, beauty products, concrete, cement, etc., and to clearly display this data using a display method known as an aquagram. However, to date, almost no research has been done using GPT to generate an average image (image data of a congruent child) from multiple image data. However, there are many examples using other generative AI services. In light of this trend, in this pilot study, we present and propose a method for the automatically generating sets of average aquagram images related to utilizing generative AI: (1) ChatGPT o4 including Matplot Library (lib) and (2) Artbreeder based on some characteristics of face skin datasets; in this study, we select four different groups of datasets on skin moisture content and moisture transpiration. Furthermore, we discuss and describe the usefulness related to the method. In the future, we envision that the proposed methodology could prove highly beneficial in contexts such as beauty salons and customer service centers of cosmetic companies. Specifically, this approach involves comparing the aquagram data of customers’ skin with aquagrams previously generated by the aforementioned AI model for different skin types. By presenting these comparisons visually to customers, we anticipate that they could be better equipped to make informed decisions regarding their skincare routines. This includes selecting appropriate serums and supplements, thereby enhancing the accuracy and effectiveness of their skincare choices.