Publications

@article{morala-arguello_application_2009,

title = {Application of textural descriptors for the evaluation of surface roughness class in the machining of metals},

author = {Patricia Morala-Argüello and Joaquín Barreiro and Enrique Alegre and Víctor González-Castro},

url = {https://scholar.google.es/citations?view_op=view_citation&hl=en&user=opCbArQAAAAJ&cstart=20&pagesize=80&sortby=title&citation_for_view=opCbArQAAAAJ:UebtZRa9Y70C},

year  = {2009},

date = {2009-01-01},

urldate = {2009-01-01},

abstract = {Surface roughness measurement has been a key topic in metal machining research for decades. Traditional methods rely on tactile devices providing 2D profiles, but advances in computer vision now enable 3D surface characterization. This paper proposes a computer vision-based method to evaluate machined part quality using five feature vectors: Hu, Flusser, Taubin, Zernike, and Legendre moments. Images were classified into low and high roughness using k-NN and neural networks. Results show that Zernike and Legendre descriptors perform best, achieving a 6.5% error rate with k-NN classification.},

keywords = {Computer vision, machine learning, machining, quality control, surface roughness},

pubstate = {published},

tppubtype = {article}

}