A Fast algorithm for active contours and curvature estimation

Williams, Dustin L.; Shah, Mubarak

doi:10.1016/1049-9660(92)90003-l

Cited by 905 publications

(454 citation statements)

References 2 publications

Supporting

Mentioning

447

Contrasting

Unclassified

Order By: Relevance

“…A hybrid of real coded genetic algorithms [5] (RCGA) and greedy algorithm [13] for mesh optimization was used in [11]. The algorithm is abbreviated here as GAGR and it is as follows 1.…”

Section: Minimization Methods Based On Genetic Algorithmsmentioning

confidence: 99%

“…One of these is placed inside of the sought surface and the other is placed outside of it. Thereafter, the energy of the mesh with higher energy is minimized locally by the greedy algorithm [13] with the constraint that outer mesh must shrink and the inner mesh must grow in size. If the mesh of higher energy is stuck on a local minima, its energy function is modified by adding a penalty for the current position of the mesh [10].…”

Section: Dual Surface Minimizationmentioning

confidence: 99%

See 1 more Smart Citation

Surface Extraction from Volumetric Images Using Deformable Meshes: A Comparative Study

Tohka

2002

Computer Vision — ECCV 2002

View full text Add to dashboard Cite

Abstract. Deformable models are by their formulation able to solve surface extraction problem from noisy volumetric images. This is since they use image independent information, in form of internal energy or internal forces, in addition to image data to achieve the goal. However, it is not a simple task to deform initially given surface meshes to a good representation of the target surface in the presence of noise. Several methods to do this have been proposed and in this study a few recent ones are compared. Basically, we supply an image and an arbitrary but reasonable initialization and examine how well the target surface is captured with different methods for controlling the deformation of the mesh. Experiments with synthetic images as well as medical images are performed and results are reported and discussed. With synthetic images, the quality of results is measured also quantitatively. No optimal method was found, but the properties of different methods in distinct situations were highlighted.

show abstract

“…A hybrid of real coded genetic algorithms [5] (RCGA) and greedy algorithm [13] for mesh optimization was used in [11]. The algorithm is abbreviated here as GAGR and it is as follows 1.…”

Section: Minimization Methods Based On Genetic Algorithmsmentioning

confidence: 99%

Section: Dual Surface Minimizationmentioning

confidence: 99%

Surface Extraction from Volumetric Images Using Deformable Meshes: A Comparative Study

Tohka

2002

Computer Vision — ECCV 2002

View full text Add to dashboard Cite

show abstract

“…Active contours [16,17,35] identified tag line locations in the undeformed and deformed cartilage [25]. The region of interest around the cartilage was enlarged to ultimately facilitate an open cubic B-spline model description of deformation at the tissue boundary using at least two additional contours beyond the boundary [19].…”

Section: Cdtr Techniquementioning

confidence: 99%

Heterogeneous three-dimensional strain fields during unconfined cyclic compression in bovine articular cartilage explants

2005

View full text Add to dashboard Cite

Articular cartilage provides critical load-bearing and tribological properties to the normal function of diarthrodial joints. The unique properties of cartilage, as well as heterogeneous deformations during mechanical compression, are due to the nonuniform microstructural organization of tissue components such as collagens and proteoglycans. A new cartilage deformation by tag registration (CDTR) technique has been developed by the authors to determine heterogeneous deformations in articular cartilage explants. The technique uses a combination of specialized MRI methods, a custom cyclic loading apparatus, and image processing software. The objective of this study was to use the CDTR technique to document strain patterns throughout the volume of normal bovine articular cartilage explants during cyclic unconfined compression at two physiologically-relevant applied normal stress levels (1.29 and 2.57 MPa). Despite simple uniaxial cyclic compressive loading with a flat, nonporous indenter, strain patterns were heterogeneous. Strains in the thickness direction (Eyy) were compressive, varied nonlinearly with depth from the articular surface from a maximum magnitude of 11% at the articular surface, and were comparable despite a 2-fold increase in applied normal stress. Strains perpendicular to the thickness direction (Exx and Ezz) were tensile, decreased linearly with depth from the articular surface from a maximum of 7%, and increased in magnitude 2.5-fold with a 2-fold increase in applied normal stress. Shear strains in the transverse plane (Ex:) were approximately zero while shear strains in the other two planes were much larger and increased in magnitude with depth from the articular surface, reaching maximum magnitudes of 2% at the articular cartilage-subchondral bone interface. In general, strain patterns indicated that cartilage osteochondral explants exhibited depth-dependent nonisotropic behavior during uniaxial cyclic loading. These results are useful in verifying constitutive formulations of articular cartilage during cyclic unconfined compression and in characterizing the micromechanical environment likely experienced by individual chondrocytes throughout the tissue volume.

show abstract

“…Also change from lip to teeth snake does not follow the proper path. Snake algorithm adapts the algorithm of Williams and Shah [6]. In this algorithm the overall energy term is reformulated as…”

Section: A Snake Methodsmentioning

confidence: 99%

Automatic Lip Tracking and Extraction of Lip Geometric Features for Lip Reading

Morade¹,

Patnaik²

2013

IJMLC

View full text Add to dashboard Cite

Abstract-Lip tracking is very crucial for visual lip reading recognition system. This paper presents a novel active contour guided geometrical feature extraction approach for lip reading. Three active contour methods are studied, namely snake, region scalable fitting energy method and loacalised active contour model. These methods are adopted for salient geometrical feature calculation. A joint feature model, obtained by combinatining inner area, height and width has been proposed. Results of experimentations on digit utterances are given to show the improvement achieved by visual speech recognition systems.Index Terms-Localised active contour model, lip tracking, principal component analysis, region scalable fitting energy method.

show abstract

A Fast algorithm for active contours and curvature estimation

Cited by 905 publications

References 2 publications

Surface Extraction from Volumetric Images Using Deformable Meshes: A Comparative Study

Surface Extraction from Volumetric Images Using Deformable Meshes: A Comparative Study

Heterogeneous three-dimensional strain fields during unconfined cyclic compression in bovine articular cartilage explants

Automatic Lip Tracking and Extraction of Lip Geometric Features for Lip Reading

Contact Info

Product

Resources

About