Um Modelo de Rede Neural Convolucional para Classificação de Peças de Vestuário

An algorithm capable of identifying clothing parts can be very useful for identifying a person ́s social identity, among other applications. Convolutional neural networks models have been shown to be efficient in the task of image classification. This paper explores and analyzes models of convolutional neural networks in the task of classifying clothing parts by images. The models presented in this paper showed higher accuracy compared to non-convolutional models of the literature.