Classificação de queixas dermatológicas usando redes neurais convolucionais.

Abstract

Cosmetic complaints, even though they do not pose life-threatening risks, can have a significant impact on people's self-esteem and consequently cause harm to their emotional well-being. In order to assist professionals in the field of aesthetics in identifying and treating these problems, the creation of an application has been proposed. This application includes functionalities such as the classification of cosmetic complaints, such as dehydration, acne, oiliness, blackheads, wrinkles, sagging, hyperpigmentation, and skin lesions. By using machine learning techniques, especially convolutional neural networks, image classification has become increasingly accurate. Based on this, the objective of this project is to use convolutional neural networks to create a model that can integrate with the aforementioned application, aiming to classify these cosmetic complaints. To achieve this, a model will be trained with a dataset containing images of each type of complaint, enabling the classification of images sent by the user and the identification of the complaints present in them.