The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Este artigo propõe um método para detectar elipses de uma imagem apesar de (1) múltiplas cores dentro das elipses, (2) limites de elipses parcialmente ocluídos, (3) limites de elipses barulhentos e localmente deformados, (4) presença de múltiplos objetos além de as elipses na imagem e (5) combinações de (1) a (4). Depois que as curvas de limite são obtidas por detecção de borda, utilizando as curvas de diferença de primeira ordem da orientação da borda de cada pixel nas curvas de limite, um método de reconexão de segmento obtém clusters de limite. Então, um RANSAC modificado detecta elipses escolhendo cinco pixels aleatoriamente dos clusters de limite, onde as elipses sobrepostas são mescladas. Resultados experimentais utilizando imagens sintetizadas e imagens reais demonstram a eficácia do método proposto juntamente com a comparação com a Transformada de Hough Randomizada, um método convencional bem conhecido.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Yingdi XIE, Jun OHYA, "Elliptical Object Detection by a Modified RANSAC with Sampling Constraint from Boundary Curves' Clustering" in IEICE TRANSACTIONS on Information,
vol. E93-D, no. 3, pp. 611-623, March 2010, doi: 10.1587/transinf.E93.D.611.
Abstract: This paper proposes a method for detecting ellipses from an image despite (1) multiple colors within the ellipses, (2) partially occluded ellipses' boundaries, (3) noisy, locally deformed boundaries of ellipses, (4) presence of multiple objects other than the ellipses in the image, and (5) combinations of (1) through (4). After boundary curves are obtained by edge detection, by utilizing the first-order difference curves of the edge orientation of each pixel in the boundary curves, a segment-reconnect method obtains boundary clusters. Then, a modified RANSAC detects ellipses by choosing five pixels randomly from the boundary clusters, where overlapped ellipses are merged. Experimental results using synthesized images and real images demonstrate the effectiveness of the proposed method together with comparison with the Randomized Hough Transform, a well-known conventional method.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E93.D.611/_p
Copiar
@ARTICLE{e93-d_3_611,
author={Yingdi XIE, Jun OHYA, },
journal={IEICE TRANSACTIONS on Information},
title={Elliptical Object Detection by a Modified RANSAC with Sampling Constraint from Boundary Curves' Clustering},
year={2010},
volume={E93-D},
number={3},
pages={611-623},
abstract={This paper proposes a method for detecting ellipses from an image despite (1) multiple colors within the ellipses, (2) partially occluded ellipses' boundaries, (3) noisy, locally deformed boundaries of ellipses, (4) presence of multiple objects other than the ellipses in the image, and (5) combinations of (1) through (4). After boundary curves are obtained by edge detection, by utilizing the first-order difference curves of the edge orientation of each pixel in the boundary curves, a segment-reconnect method obtains boundary clusters. Then, a modified RANSAC detects ellipses by choosing five pixels randomly from the boundary clusters, where overlapped ellipses are merged. Experimental results using synthesized images and real images demonstrate the effectiveness of the proposed method together with comparison with the Randomized Hough Transform, a well-known conventional method.},
keywords={},
doi={10.1587/transinf.E93.D.611},
ISSN={1745-1361},
month={March},}
Copiar
TY - JOUR
TI - Elliptical Object Detection by a Modified RANSAC with Sampling Constraint from Boundary Curves' Clustering
T2 - IEICE TRANSACTIONS on Information
SP - 611
EP - 623
AU - Yingdi XIE
AU - Jun OHYA
PY - 2010
DO - 10.1587/transinf.E93.D.611
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E93-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2010
AB - This paper proposes a method for detecting ellipses from an image despite (1) multiple colors within the ellipses, (2) partially occluded ellipses' boundaries, (3) noisy, locally deformed boundaries of ellipses, (4) presence of multiple objects other than the ellipses in the image, and (5) combinations of (1) through (4). After boundary curves are obtained by edge detection, by utilizing the first-order difference curves of the edge orientation of each pixel in the boundary curves, a segment-reconnect method obtains boundary clusters. Then, a modified RANSAC detects ellipses by choosing five pixels randomly from the boundary clusters, where overlapped ellipses are merged. Experimental results using synthesized images and real images demonstrate the effectiveness of the proposed method together with comparison with the Randomized Hough Transform, a well-known conventional method.
ER -