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
Nous proposons une modification des techniques généralisées de champ d'écoulement de vecteurs de gradient basées sur des techniques d'analyse multirésolution et de portrait de phase. L'image originale est soumise à une analyse multirésolution pour créer une séquence d'images d'approximation et de détail. Les approximations sont converties en une carte de bord puis en un champ de gradient soumis à la transformation de flux vectoriel de gradient généralisée. La procédure supprime le bruit et étend les grands gradients. À chaque itération, l'algorithme obtient un nouveau champ vectoriel amélioré filtré à l'aide de l'analyse du portrait de phase. Le portrait de phase est appliqué sur une fenêtre de taille variable pour trouver les points limites possibles et le bruit. Contrairement aux techniques de portrait de phase précédentes basées sur des règles binaires, notre méthode génère un score continu et ajustable. Le score est fonction des valeurs propres du système linéarisé correspondant d'équations différentielles ordinaires. La caractéristique principale de la méthode est la continuité : lorsque le score est élevé, il s’agit probablement de la partie bruyante de l’image, mais lorsque le score est faible, il s’agit probablement de la limite de l’objet. La partition est utilisée par un filtre appliqué à l'image originale. Au voisinage des points ayant un score élevé, le niveau de gris est lissé tandis qu'aux points limites, le niveau de gris est augmenté. Ensuite, un nouveau champ de gradient est généré et le résultat est incorporé dans les itérations itératives du flux vectoriel de gradient. Cette approche combinée à l'analyse multirésolution conduit à des segmentations robustes avec une amélioration impressionnante de la précision. Nos expériences numériques avec des images échographiques médicales synthétiques et réelles montrent que la technique proposée surpasse la méthode conventionnelle de flux vectoriel à gradient même lorsque les filtres et la multirésolution sont appliqués de la même manière. Enfin, nous montrons que l'algorithme proposé permet au contour initial d'être beaucoup plus éloigné de la frontière réelle que ce qui est possible avec les méthodes conventionnelles.
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.
Copier
Sirikan CHUCHERD, Annupan RODTOOK, Stanislav S. MAKHANOV, "Phase Portrait Analysis for Multiresolution Generalized Gradient Vector Flow" in IEICE TRANSACTIONS on Information,
vol. E93-D, no. 10, pp. 2822-2835, October 2010, doi: 10.1587/transinf.E93.D.2822.
Abstract: We propose a modification of the generalized gradient vector flow field techniques based on multiresolution analysis and phase portrait techniques. The original image is subjected to mutliresolutional analysis to create a sequence of approximation and detail images. The approximations are converted into an edge map and subsequently into a gradient field subjected to the generalized gradient vector flow transformation. The procedure removes noise and extends large gradients. At every iteration the algorithm obtains a new, improved vector field being filtered using the phase portrait analysis. The phase portrait is applied to a window with a variable size to find possible boundary points and the noise. As opposed to previous phase portrait techniques based on binary rules our method generates a continuous adjustable score. The score is a function of the eigenvalues of the corresponding linearized system of ordinary differential equations. The salient feature of the method is continuity: when the score is high it is likely to be the noisy part of the image, but when the score is low it is likely to be the boundary of the object. The score is used by a filter applied to the original image. In the neighbourhood of the points with a high score the gray level is smoothed whereas at the boundary points the gray level is increased. Next, a new gradient field is generated and the result is incorporated into the iterative gradient vector flow iterations. This approach combined with multiresolutional analysis leads to robust segmentations with an impressive improvement of the accuracy. Our numerical experiments with synthetic and real medical ultrasound images show that the proposed technique outperforms the conventional gradient vector flow method even when the filters and the multiresolution are applied in the same fashion. Finally, we show that the proposed algorithm allows the initial contour to be much farther from the actual boundary than possible with the conventional methods.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E93.D.2822/_p
Copier
@ARTICLE{e93-d_10_2822,
author={Sirikan CHUCHERD, Annupan RODTOOK, Stanislav S. MAKHANOV, },
journal={IEICE TRANSACTIONS on Information},
title={Phase Portrait Analysis for Multiresolution Generalized Gradient Vector Flow},
year={2010},
volume={E93-D},
number={10},
pages={2822-2835},
abstract={We propose a modification of the generalized gradient vector flow field techniques based on multiresolution analysis and phase portrait techniques. The original image is subjected to mutliresolutional analysis to create a sequence of approximation and detail images. The approximations are converted into an edge map and subsequently into a gradient field subjected to the generalized gradient vector flow transformation. The procedure removes noise and extends large gradients. At every iteration the algorithm obtains a new, improved vector field being filtered using the phase portrait analysis. The phase portrait is applied to a window with a variable size to find possible boundary points and the noise. As opposed to previous phase portrait techniques based on binary rules our method generates a continuous adjustable score. The score is a function of the eigenvalues of the corresponding linearized system of ordinary differential equations. The salient feature of the method is continuity: when the score is high it is likely to be the noisy part of the image, but when the score is low it is likely to be the boundary of the object. The score is used by a filter applied to the original image. In the neighbourhood of the points with a high score the gray level is smoothed whereas at the boundary points the gray level is increased. Next, a new gradient field is generated and the result is incorporated into the iterative gradient vector flow iterations. This approach combined with multiresolutional analysis leads to robust segmentations with an impressive improvement of the accuracy. Our numerical experiments with synthetic and real medical ultrasound images show that the proposed technique outperforms the conventional gradient vector flow method even when the filters and the multiresolution are applied in the same fashion. Finally, we show that the proposed algorithm allows the initial contour to be much farther from the actual boundary than possible with the conventional methods.},
keywords={},
doi={10.1587/transinf.E93.D.2822},
ISSN={1745-1361},
month={October},}
Copier
TY - JOUR
TI - Phase Portrait Analysis for Multiresolution Generalized Gradient Vector Flow
T2 - IEICE TRANSACTIONS on Information
SP - 2822
EP - 2835
AU - Sirikan CHUCHERD
AU - Annupan RODTOOK
AU - Stanislav S. MAKHANOV
PY - 2010
DO - 10.1587/transinf.E93.D.2822
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E93-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2010
AB - We propose a modification of the generalized gradient vector flow field techniques based on multiresolution analysis and phase portrait techniques. The original image is subjected to mutliresolutional analysis to create a sequence of approximation and detail images. The approximations are converted into an edge map and subsequently into a gradient field subjected to the generalized gradient vector flow transformation. The procedure removes noise and extends large gradients. At every iteration the algorithm obtains a new, improved vector field being filtered using the phase portrait analysis. The phase portrait is applied to a window with a variable size to find possible boundary points and the noise. As opposed to previous phase portrait techniques based on binary rules our method generates a continuous adjustable score. The score is a function of the eigenvalues of the corresponding linearized system of ordinary differential equations. The salient feature of the method is continuity: when the score is high it is likely to be the noisy part of the image, but when the score is low it is likely to be the boundary of the object. The score is used by a filter applied to the original image. In the neighbourhood of the points with a high score the gray level is smoothed whereas at the boundary points the gray level is increased. Next, a new gradient field is generated and the result is incorporated into the iterative gradient vector flow iterations. This approach combined with multiresolutional analysis leads to robust segmentations with an impressive improvement of the accuracy. Our numerical experiments with synthetic and real medical ultrasound images show that the proposed technique outperforms the conventional gradient vector flow method even when the filters and the multiresolution are applied in the same fashion. Finally, we show that the proposed algorithm allows the initial contour to be much farther from the actual boundary than possible with the conventional methods.
ER -