Force field analysis snake: an improved parametric active contour model

Hou, Zhiqiang; Han, Chongzhao

doi:10.1016/j.patrec.2004.09.001

Cited by 38 publications

(15 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A popular form of active contours is the Gradient Vector Flow (GVF) snake that computes a gradient vector potential force field by applying a diffusion process to a traditional potential force field, dispersing the larger magnitude forces out towards homogeneous regions [41]. Similarly, the Force Field Analysis (FFA) snake analyses the properties of the force field to identify and move boundary points that have incorrectly converged [18].…”

Section: The Deformable Model -Kass Snakementioning

confidence: 99%

High Resolution Tracking of Cell Membrane Dynamics in Moving Cells: an Electrifying Approach

Tyson

Epstein

Anderson

et al. 2010

Math. Model. Nat. Phenom.

View full text Add to dashboard Cite

Abstract. Cell motility is an integral part of a diverse set of biological processes. The quest for mathematical models of cell motility has prompted the development of automated approaches for gathering quantitative data on cell morphology, and the distribution of molecular players involved in cell motility. Here we review recent approaches for quantifying cell motility, including automated cell segmentation and tracking. Secondly, we present our own novel method for tracking cell boundaries of moving cells, the Electrostatic Contour Migration Method (ECMM), as an alternative to the generally accepted level set method (LSM). ECMM smoothly tracks regions of the cell boundary over time to compute local membrane displacements using the simple underlying concept of electrostatics. It offers substantial speed increases and reduced computational overheads in comparison to the LSM. We conclude with general considerations regarding boundary tracking in the context of mathematical modelling.

show abstract

Section: The Deformable Model -Kass Snakementioning

confidence: 99%

High Resolution Tracking of Cell Membrane Dynamics in Moving Cells: an Electrifying Approach

Tyson

Epstein

Anderson

et al. 2010

Math. Model. Nat. Phenom.

View full text Add to dashboard Cite

show abstract

“…The main idea of the discrete orientation force field analysis (DOFFA) proposed by Hou and Han [40] is that the true boundary vectors must face each other along a certain direction. Therefore, DOFFA introduces a 3×3 sampling window around the candidate boundary point and analyses the directions of the vector field in this window.…”

Section: Orientation Force Field Analysis and Phase Portrait Techniquesmentioning

confidence: 99%

“…In this paper, we propose a special numerical treatment of the GGVF equations to improve the accuracy and convergence of the snake subjected to the resulting vector field. Our modification called phase portrait orientation force field analysis (PPA) inspired by discrete force field analysis proposed in [40] uses intermediate vector fields obtained during the numerical iterations to construct an improved edge map.…”

Section: Introductionmentioning

confidence: 99%

Phase Portrait Analysis for Multiresolution Generalized Gradient Vector Flow

Chucherd

Rodtook

Makhanov

2010

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYWe 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. key words: phase portrait analysis, multiresolution analysis, medical image processing

show abstract

“…In order to solve the first drawback, related to the iterations required for reaching the final situation, the contour can be insensitive to the initialization analyzing the external force distribution [4] or with a non linear diffusion of the gradient information [5][6][7]. Also, the parameters can be estimated with an adaptive snake [8] avoiding instabilities and improving the shape reconstruction, or setting the bounds of the elasticity and rigidity parameters knowing the shape of the object [9] or without knowing the shape but using a Kalman filter for automatically adapting these parameters [10].…”

Section: Introductionmentioning

confidence: 99%