Encoding of a priori information in active contour models

Olstad, Bjørn Harald; Torp, Anders Herman

doi:10.1109/34.537341

Cited by 37 publications

(12 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Furthermore, the original snake method is a parametric method and the contour cannot change topology during its deformation process without an additional mechanism. With these limitations, a number of deformable contour methods have been proposed to improve the original snake, such as snake variations [2][3][4]10,20,22,25,26,37,39,[45][46][47].…”

Section: Snakesmentioning

confidence: 99%

A comparative study of deformable contour methods on medical image segmentation

Peng

Everding

et al. 2008

Image and Vision Computing

235

101

View full text Add to dashboard Cite

Section: Snakesmentioning

confidence: 99%

A comparative study of deformable contour methods on medical image segmentation

Peng

Everding

et al. 2008

Image and Vision Computing

235

101

View full text Add to dashboard Cite

“…Also, the magnitude of the external forces become smaller very quickly while evolving from the image boundaries which causes small capture range of snakes. Therefore, variations of the parametric active contour method have been proposed [43][44][45][46][47][48][49][50] by using edge-based or region-based external forces to handle topological changes or shape-based prior knowledge to avoid spurious edges.…”

Section: Active Contours For Image Segmentationmentioning

confidence: 99%

An automatic level set based liver segmentation from MRI data sets

Göçeri

Unlu

Güzeliş

et al. 2012

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

View full text Add to dashboard Cite

Abstract-A fast and accurate liver segmentation method is a challenging work in medical image analysis area. Liver segmentation is an important process for computer-assisted diagnosis, pre-evaluation of liver transplantation and therapy planning of liver tumors. There are several advantages of magnetic resonance imaging such as free form ionizing radiation and good contrast visualization of soft tissue. Also, innovations in recent technology and image acquisition techniques have made magnetic resonance imaging a major tool in modern medicine. However, the use of magnetic resonance images for liver segmentation has been slow when we compare applications with the central nervous systems and musculoskeletal. The reasons are irregular shape, size and position of the liver, contrast agent effects and similarities of the gray values of neighbor organs. Therefore, in this study, we present a fully automatic liver segmentation method by using an approximation of the level set based contour evolution from T2 weighted magnetic resonance data sets. The method avoids solving partial differential equations and applies only integer operations with a two-cycle segmentation algorithm. The efficiency of the proposed approach is achieved by applying the algorithm to all slices with a constant number of iteration and performing the contour evolution without any user defined initial contour. The obtained results are evaluated with four different similarity measures and they show that the automatic segmentation approach gives successful results.

show abstract

“…Dubuisson et al [64] used a set of hand-drafted constraints to explicitly restrict the deformation of a deformable polygon for representing cars of di erent types. Besides, Olstad et al [99] used syntactical approaches to incorporate constraints, where a priori information about object shape can be encoded into an active contour model as a set of grammar rules. Also, Fua et al [100] conÿned the model parameter search in the orthogonal subspaces of some given hard constraint surfaces.…”

Section: Constraint Incorporation Using Prior Knowledgementioning

confidence: 99%

On deformable models for visual pattern recognition

Cheung

Yeung

Chin

2002

Pattern Recognition

View full text Add to dashboard Cite

This paper reviews model-based methods for non-rigid shape recognition. These methods model, match and classify non-rigid shapes, which are generally problematic for conventational algorithms using rigid models. Issues including model representation, optimization criteria formulation, model matching, and classiÿcation are examined in detail with the objective to provide interested researchers a roadmap for exploring the ÿeld. This paper emphasizes on 2D deformable models. Their potential applications and future research directions, particularly on deformable pattern classiÿcation, are discussed. ?

show abstract

Encoding of a priori information in active contour models

Cited by 37 publications

References 13 publications

A comparative study of deformable contour methods on medical image segmentation

A comparative study of deformable contour methods on medical image segmentation

An automatic level set based liver segmentation from MRI data sets

On deformable models for visual pattern recognition

Contact Info

Product

Resources

About