Improving Facial Expression Recognition Through Data Preparation and Merging
Por favor, use este identificador para citar o enlazar este ítem:
http://hdl.handle.net/10045/136107
Título: | Improving Facial Expression Recognition Through Data Preparation and Merging |
---|---|
Autor/es: | Mejia-Escobar, Christian | Cazorla, Miguel | Martinez-Martin, Ester |
Grupo/s de investigación o GITE: | Robótica y Visión Tridimensional (RoViT) |
Centro, Departamento o Servicio: | Universidad de Alicante. Departamento de Ciencia de la Computación e Inteligencia Artificial |
Palabras clave: | Artificial dataset | Deep Learning | Convolutional Neural Network | Emotion Recognition | Facial Expression Recognition | Stable Diffusion |
Fecha de publicación: | 10-jul-2023 |
Editor: | IEEE |
Cita bibliográfica: | IEEE Access. 2023, 11: 71339-71360. https://doi.org/10.1109/ACCESS.2023.3293728 |
Resumen: | Human emotions present a major challenge for artificial intelligence. Automated emotion recognition based on facial expressions is important to robotics, medicine, psychology, education, security, arts, entertainment and more. Deep learning is promising for capturing complex emotional features. However, there is no training dataset that is large and representative of the full diversity of emotional expressions in all populations and contexts. Current facial datasets are incomplete, biased, unbalanced, error-prone and have different properties. Models learn these limitations and become dependent on specific datasets, hindering their ability to generalize to new data or real-world scenarios. Our work addresses these difficulties and provides the following contributions to improve emotion recognition: 1) a methodology for merging disparate in-the-wild datasets that increases the number of images and enriches the diversity of people, gestures, and attributes of resolution, color, background, lighting and image format; 2) a balanced, unbiased, and well-labeled evaluator dataset, built with a gender, age, and ethnicity predictor and the successful Stable Diffusion model. Single- and cross-dataset experimentation show that our method increases the generalization of the FER2013, NHFI and AffectNet datasets by 13.93%, 24.17% and 7.45%, respectively; and 3) we propose the first and largest artificial emotion dataset, which can complement real datasets in tasks related to facial expression. |
Patrocinador/es: | This work has been funded by grant CIPROM/2021/017 awarded by the MEEBAI Project (Prometheus Programme for Research Groups on R&D Excellence) from Conselleria de Innovación, Universidades, Ciencia y Sociedad Digital of Generalitat Valenciana (Spain), and partially by the grant awarded by the Central University of Ecuador through budget certification No. 34 of March 25, 2022 for the development of the research project with code DOCT-DI-2020-37. |
URI: | http://hdl.handle.net/10045/136107 |
ISSN: | 2169-3536 |
DOI: | 10.1109/ACCESS.2023.3293728 |
Idioma: | eng |
Tipo: | info:eu-repo/semantics/article |
Derechos: | This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License. For more information, see https://creativecommons.org/licenses/by-nc-nd/4.0/ |
Revisión científica: | si |
Versión del editor: | https://doi.org/10.1109/ACCESS.2023.3293728 |
Aparece en las colecciones: | INV - RoViT - Artículos de Revistas |
Archivos en este ítem:
Archivo | Descripción | Tamaño | Formato | |
---|---|---|---|---|
Mejia-Escobar_etal_2023_IEEE-Access.pdf | 3,3 MB | Adobe PDF | Abrir Vista previa | |
Este ítem está licenciado bajo Licencia Creative Commons