Aplicação de uma Rede de Análise Paraconsistente (RAP) como sistema de classificação binário de imagens de ligas metálicas a partir de estudos de seleção de parâmetros
Abstract
Palavras-chave: Redes de Análise Paraconsistentes; Visão Computacional; Classificação de Imagens; Texturas de Haralick.
Application of a Paraconsistent Analysis Network (PANnet) as a binary classification system of metallic alloys images based on the studies of parameters selection
Abstract: This paper describes the study of parameters selection and the process of creating a PANnet capable of performing the binary classification of images for the presence or absence of rust in images of metallic alloys. It is shown that the processing of Haralick’s texture feature descriptors by the structures provided by the Paraconsistent Logic (PL), with the threshold calculated via the Receiver Operating Characteristic Curve (ROC Curve), allows the creation of a classification system with 75% accuracy and a calculated f-score of 0.78.
Keywords: Paraconsistent Analysis Networks; Computer Vision; Images Classification; Haralick Textures.
Refbacks
- There are currently no refbacks.