Towards Explainable Cuisine Prediction for Recipes with Image Color Analysis

Food is an important factor when choosing a touristic destination, and culinary images are a fundamental tool in gastronomic marketing. This paper presents an approach to analyse the use of color in food images based on a dataset of more than 22000 recipes coming form a popular recipe website, inclu...

Descripción completa

Detalles Bibliográficos
Autores: Casales García, Vicente, Sanz, I., Museros, Lledó, González Abril, Luis
Tipo de recurso: capítulo de libro
Estado:Versión publicada
Fecha de publicación:2024
País:España
Institución:Universidad de Sevilla (US)
Repositorio:idUS. Depósito de Investigación de la Universidad de Sevilla
OAI Identifier:oai:idus.us.es:11441/180100
Acceso en línea:https://hdl.handle.net/11441/180100
https://doi.org/10.3233/FAIA240444
Access Level:acceso abierto
Palabra clave:Gastronomy
Cuisine of World
Natural Language Processing
Kruskal- Wallis
Descripción
Sumario:Food is an important factor when choosing a touristic destination, and culinary images are a fundamental tool in gastronomic marketing. This paper presents an approach to analyse the use of color in food images based on a dataset of more than 22000 recipes coming form a popular recipe website, including images of the final dishes and scores that indicate how well the recipe was valued by users. First, the specific cuisine of each recipe is inferred by using the Llama 3 Large Language Model (LLM). The main color of the dish images is also determined. Fi- nally, statistically significant relationships between scores and cuisine labels is also determined. Our preliminary results show some relevant results for tourist market- ing, such as showing the most popular cuisines.