Acne Severity Classification Using Convolutional Neural Networks (Classificação de Severidade de Acne Utilizando Redes Neurais Convolucionais)
Year: 2025
Type: article
Abstract: This article aims to perform a comparative analysis and identify the best artificial intelligence model for acne classification, based on the IGA (Investigator Global Assessment of Acne), used by the FDA (Food and Drug Administration), a federal agency that is related to health and human services in the United States. Two models were used: (1) a learning model using neural networks based on CNN (Convolutional Neural Network); and (2) a second nonlinear Support Vector Machine (SVM) model that is used for classification and regression. A dataset consisting of 84 facial images was used, containing techniques for rotating these images for better generalization of the model. As results obtained, it is highlighted that the acne recognition model using convolutional neural networks had an accuracy of 85% on the test dataset.
Authors: Rodrigues, Italo G. S., Hermann, Rodrigo G., Oliveira, Enan L., Lauand, Mauricélio, Miranda, Marise
Language: English
Subfield: Dermatology
Field: Medicine
Domain: Health Sciences
Open Access status: green
OpenAlex ID: W6911988847
FWCI:
Cites:
Cited by:
Related to: