Publications

@article{garcia_ordas_azibo_2015,

title = {aZIBO shape descriptor for monitoring tool wear in milling},

author = {María Teresa García-Ordás and Enrique Alegre and Víctor González-Castro and Óscar García-Olalla Olivera and Joaquín Barreiro and Ana Isabel Fernández-Abia},

url = {https://www.sciencedirect.com/science/article/pii/S1877705815044951},

year  = {2015},

date = {2015-01-01},

urldate = {2015-01-01},

journal = {Procedia Engineering},

volume = {132},

pages = {958–965},

abstract = {This paper proposes an automated method for estimating insert wear in metal machining to optimize tool replacement. The aZIBO shape descriptor (absolute Zernike moments with Invariant Boundary Orientation) is used for wear characterization. A dataset of 577 wear regions was classified into two (Low-High) and three (Low-Medium-High) classes using kNN and SVM classifiers. aZIBO outperformed traditional shape descriptors, achieving success rates of 91.33% for two-class and 90.12% for three-class classification.},

note = {Publisher: No longer published by Elsevier},

keywords = {image processing, machine learning, metal machining, shape descriptors, tool wear detection},

pubstate = {published},

tppubtype = {article}

}