Título: Moment Invariant based Classification of Objects from low-resolution Industrial Sensor Images
Autores: Silva, Rodrigo D. C.; Thé, George A. P.
Resumo: In this paper, the issue of object recognition for industrial applications, using images extracted from a 3D sensor is discussed. We focus on moment invariants based feature extraction algorithms for the classification of images from an industrial 3D sensor, using the Optimum-Path Forest (OPF) classifier, a recent and promising method for pattern recognition, with a fast training algorithm and good accuracy results. Classification performance has been compared in terms of extraction time and accuracy for five moment invariant algorithms, Hu, Legendre, Zernike, Fourier-Mellin and Tchebichef moments, and for three objects different in size, revealing that Tchebichef moments is superior.
Palavras-chave: Moment Invariants; Optimum-Path Forest(OPF); 3D Sensor; Computer Vision
Código DOI: 10.21528/CBIC2013-250
Artigo em pdf: bricsccicbic2013_submission_250.pdf
Arquivo BibTex: bricsccicbic2013_submission_250.bib