Coefficient of Variation Based Image Selective Segmentation Model Using Active Contours

Badshah, Noor; Chen, Ke; Ali, Haider; Murtaza, Ghulam

doi:10.4208/eajam.090312.080412a

Cited by 38 publications

(30 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A second method for improving (6) is to replace the L 2 fitting of Mumford-Shah or Chan-Vese type by a coefficient of variation fitting term as in [7]:…”

Section: Y)g(|∇z(x Y)|)|∇h(ϕ(x Y))|dωmentioning

confidence: 99%

Selective variational image segmentation combined with registration: Models and algorithms

Chen

2012

2012 3rd International Conference on Image Processing Theory, Tools and Applications (IPTA)

Self Cite

View full text Add to dashboard Cite

In this paper, I present some new and joint work on local and selective segmentation models and algorithms which have potential applications in medical imaging. First I review a familiar segmentation model of global energy minimization framework in two dimensions (three dimensions may be presented similarly). Then I discuss selective segmentation models and several refined models where pre-defined geometric constraints guide local segmentation. Such 2D models can be generalized to 3D and some brief experiments are given to demonstrate the ideas of the paper. Finally I discuss the use of image registration methods to obtain geometric constraints or equivalent initial contours towards an automatic segmentation framework.As mentioned, the work discussed here represents a small portion of results obtained in the Liverpool's Centre for Mathematical Imaging Techniques (CMIT) and is jointly carried out with collaborators; for this paper, these include

show abstract

“…A second method for improving (6) is to replace the L 2 fitting of Mumford-Shah or Chan-Vese type by a coefficient of variation fitting term as in [7]:…”

Section: Y)g(|∇z(x Y)|)|∇h(ϕ(x Y))|dωmentioning

confidence: 99%

Selective variational image segmentation combined with registration: Models and algorithms

Chen

2012

2012 3rd International Conference on Image Processing Theory, Tools and Applications (IPTA)

Self Cite

View full text Add to dashboard Cite

show abstract

“…is simply the normalised Euclidean distance D E (x, y) as used in the Spencer-Chen model (5). We have free rein to design f (x, y) as we wish.…”

Section: Computing the Geodesic Distance Term D M (X Y)mentioning

confidence: 99%

“…This paper is mainly concerned with selective segmentation of objects in an image, given a set of points near the object or objects to be segmented. It builds in such user input to a model using a set M = {(x i , y i ) ∈ Ω, 1 ≤ i ≤ k} where Ω ⊂ R 2 is the image domain [4,5,17]. Nguyen et al [30] considered marker sets M and A which consist of points inside and outside, respectively, the object or objects to be segmented.…”

Section: Introductionmentioning

confidence: 99%

“…Rada and Chen [36] introduced a selective segmentation method based on two-level sets which was shown to be more robust than the Badshah-Chen model. We also refer to [5,23] for selective segmentation models which include different fitting constraints, using coefficient of variation and the centroid of M respectively. None of these models have a restriction on the size of the object or objects to be detected and depending on the initialisation these methods have the potential to detect more or fewer objects than the user desired.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Convex Geodesic Selective Model for Image Segmentation

2018

Self Cite

View full text Add to dashboard Cite

Selective segmentation is an important application of image processing. In contrast to global segmentation in which all objects are segmented, selective segmentation is used to isolate specific objects in an image and is of particular interest in medical imaging -permitting segmentation and review of a single organ. An important consideration is to minimise the amount of user input to obtain the segmentation; this differs from interactive segmentation in which more user input is allowed than selective segmentation. To achieve selection, we propose a selective segmentation model which uses the edge-weighted geodesic distance from a marker set as a penalty term. It is demonstrated that this edge-weighted geodesic penalty term improves on previous selective penalty terms. A convex formulation of the model is also presented, allowing arbitrary initialisation. It is shown that the proposed model is less parameter dependent and requires less user input than previous models. Further modifications are made to the edgeweighted geodesic distance term to ensure segmentation robustness to noise and blur. We can show that the overall Euler-Lagrange equation admits a unique viscosity solution. Numerical results show that the result is robust to user input and permits selective segmentations that are not possible with other models.

show abstract

“…In simple words, image segmentation extracts objects by distinguishing the foreground and background in images [1][2][3][4][5][6]. Variational image segmentation models are categorized into two classes, namely edge-based models and region-based models.…”

Section: Introductionmentioning

confidence: 99%

Multiphase segmentation based on new signed pressure force functions and one level set function

Ali¹,

Badshah²,

Chen³

et al. 2017

Turk J Elec Eng & Comp Sci

Self Cite

View full text Add to dashboard Cite

Abstract:In this paper we propose a new model to detect multiple objects of various intensities in images having maximum, minimum, or middle-intensity background by evolving only one level set function. In this model, a new signed pressure force function based on novel generalized averages is used for segmentation of images with maximum or minimum intensity background. For images with middle-intensity backgrounds, which are indeed challenging for 2-phase models, we propose a new product generalized signed pressure force function. Finally, to give experimental and qualitative evidence, our model is tested on both synthetic and real images with the Jaccard similarity index. The experimental and qualitative results reveal that the proposed method is efficient in both global and selective segmentation. Our new model is also tested on color images and the results are compared with the state-of-the-art models.

show abstract

Coefficient of Variation Based Image Selective Segmentation Model Using Active Contours

Cited by 38 publications

References 19 publications

Selective variational image segmentation combined with registration: Models and algorithms

Selective variational image segmentation combined with registration: Models and algorithms

A Convex Geodesic Selective Model for Image Segmentation

Multiphase segmentation based on new signed pressure force functions and one level set function

Contact Info

Product

Resources

About