@article{suarez_pdf_nodate,
title = {PDF OFF-PRINTS},
author = {S Suárez and Enrique Alegre and Joaquín Barreiro and Patricia Morala-Arguello and Víctor González-Castro},
url = {https://www.researchgate.net/profile/J-Barreiro/publication/235792932_Classification_and_correlation_of_surface_roughness_in_metallic_parts_using_texture_descriptors/links/09e415138dec0b3b71000000/Classification-and-correlation-of-surface-roughness-in-metallic-parts-using-texture-descriptors.pdf},
abstract = {This paper presents a method for classifying surface roughness in machined metallic parts using an artificial vision system. Two texture analysis methods, GLCM and Laws' energy method, are used as descriptors. Classification is performed using LDA, QDA, and ANN, with the best results (94.23%) achieved using Neural Networks. The method successfully correlates texture descriptors with average roughness (Ra).},
keywords = {co-occurrence matrix, laws, roughness, surface texture},
pubstate = {published},
tppubtype = {article}
}
This paper presents a method for classifying surface roughness in machined metallic parts using an artificial vision system. Two texture analysis methods, GLCM and Laws' energy method, are used as descriptors. Classification is performed using LDA, QDA, and ANN, with the best results (94.23%) achieved using Neural Networks. The method successfully correlates texture descriptors with average roughness (Ra).