Resumo

ATENCIO ORTIZ, Pedro; BRANCH BEDOYA, John  e  SANCHEZ TORRES, Germán. Supervised machine learning for holes classification of three-dimensional free-form models. Ing. Desarro. [online]. 2015, vol.33, n.1, pp.18-37. ISSN 0122-3461.  https://doi.org/10.14482/inde.33.1.5437.

Hole-filling task in tridimensional reconstruction process requires an expert user to select holes to be corrected (filled) in cases where there are real holes in the surface of the object that is being reconstructed. Generally, proposed works in hole-filling tasks assume the surface of the object is continuous, so that all holes must be corrected. The latter is not true for many cases e.i. industrial parts and free-form objects. In this work, it is proposed a method for automatic hole classification in tridimensional surfaces of free-form objects into two categories: real or holes that must not be corrected, and anomalies or holes that must be corrected. For this purpose, three characteristics of hole contour are calculated: torsion, curvature and size, and subsequently are used in a supervised classification system. Results show a classification rate over 90%.

Palavras-chave : hole-filling; supervised machine learning; three-dimensional Reconstruction.

        · resumo em Espanhol     · texto em Espanhol     · Espanhol ( pdf )