Active Shape Models and the shape approximation problem

Hill, Andrew; Cootes, Timothy F.; Taylor, Chris

doi:10.1016/0262-8856(96)01097-9

Cited by 56 publications

(20 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We did not include this term in our final results but mention it to show that, in principle, ''region information'' specific to a particular structure 8,28 might be able to increase the robustness of the chamfer match. Statistical analyses of texture ͓see Richardson and Keen 32,33 and Cootes and Taylor ͑unpublished presentation, MICCAI 2001͔͒ similar to the PDMs of Hill et al 27 are another possibility.…”

Section: Discussionmentioning

confidence: 92%

A deformable-model approach to semi-automatic segmentation of CT images demonstrated by application to the spinal canal

et al. 2004

View full text Add to dashboard Cite

Because of the importance of accurately defining the target in radiation treatment planning, we have developed a deformable-template algorithm for the semi-automatic delineation of normal tissue structures on computed tomography ͑CT͒ images. We illustrate the method by applying it to the spinal canal. Segmentation is performed in three steps: ͑a͒ partial delineation of the anatomic structure is obtained by wavelet-based edge detection; ͑b͒ a deformable-model template is fitted to the edge set by chamfer matching; and ͑c͒ the template is relaxed away from its original shape into its final position. Appropriately chosen ranges for the model parameters limit the deformations of the template, accounting for interpatient variability. Our approach differs from those used in other deformable models in that it does not inherently require the modeling of forces. Instead, the spinal canal was modeled using Fourier descriptors derived from four sets of manually drawn contours. Segmentation was carried out, without manual intervention, on five CT data sets and the algorithm's performance was judged subjectively by two radiation oncologists. Two assessments were considered: in the first, segmentation on a random selection of 100 axial CT images was compared with the corresponding contours drawn manually by one of six dosimetrists, also chosen randomly; in the second assessment, the segmentation of each image in the five evaluable CT sets ͑a total of 557 axial images͒ was rated as either successful, unsuccessful, or requiring further editing. Contours generated by the algorithm were more likely than manually drawn contours to be considered acceptable by the oncologists. The mean proportions of acceptable contours were 93% ͑automatic͒ and 69% ͑manual͒. Automatic delineation of the spinal canal was deemed to be successful on 91% of the images, unsuccessful on 2% of the images, and requiring further editing on 7% of the images. Our deformable template algorithm thus gives a robust segmentation of the spinal canal on CT images. The method can be extended to other structures, although it remains to be shown that chamfer matching is sufficiently robust for the delineation of soft-tissue structures surrounded by soft tissue.

show abstract

Section: Discussionmentioning

confidence: 92%

A deformable-model approach to semi-automatic segmentation of CT images demonstrated by application to the spinal canal

et al. 2004

View full text Add to dashboard Cite

show abstract

“…In 2D they lie along curves and in 3D along surfaces. An important application of pseudo‐landmarks is in the generation of landmark sets on which active shape models are based (Hill et al. 1996).…”

Section: Analytical and Visualization Techniquesmentioning

confidence: 99%

Facial surface analysis by 3D laser scanning and geometric morphometrics in relation to sexual dimorphism in cerebral–craniofacial morphogenesis and cognitive function

et al. 2005

View full text Add to dashboard Cite

Over early fetal life the anterior brain, neuroepithelium, neural crest and facial ectoderm constitute a unitary, three-dimensional (3D) developmental process. This intimate embryological relationship between the face and brain means that facial dysmorphogenesis can serve as an accessible and informative index of brain dysmorphogenesis in neurological and psychiatric disorders of early developmental origin. There are three principal challenges in seeking to increase understanding of disorders of early brain dysmorphogenesis through craniofacial dysmorphogenesis: (i) the first, technical, challenge has been to digitize the facial surface in its inherent three-dimensionality;(ii) the second, analytical, challenge has been to develop methodologies for extracting biologically meaningful shape covariance from digitized samples, making statistical comparisons between groups and visualizing in 3D the resultant statistical models on a 'whole face' basis; (iii) the third, biological, challenge is to demonstrate a relationship between facial morphogenesis and brain morphogenesis not only in anatomical-embryological terms but also at the level of brain function. Here we consider each of these challenges in turn and then illustrate the issues by way of our own findings. These use human sexual dimorphism as an exemplar for 3D laser surface scanning of facial shape, analysis using geometric morphometrics and exploration of cognitive correlates of variation in shape of the 'whole face', in the context of studies relating to the early developmental origins of schizophrenia.

show abstract

“…2) Shape Parameter Inferring: From (5), we can write the object function for shape localization problem as (11) In the th iteration, can be optimized in the neighborhood of in term of the adaptive local likelihood distribution model, then the object function is changed to (12) Thus, the local optimum of the shape localization problem can be derived using the energy function (13) where is the corresponding energy function of the distribution , namely , is the dimension of , is the th largest eigenvalue of the covariance matrix of the training shapes, is the corresponding shape parameter, , and is the geometry transformation function based on the transformation parameter (14) where . In (13), the optimization function is multinomial and has no close form solution.…”

Section: ) Adaptive Local Likelihood Distribution Modelmentioning

confidence: 99%

“…In (13), the optimization function is multinomial and has no close form solution. As discussed in [12], the solution can be approximated iteratively using a two-step optimization method as following.…”

Section: ) Adaptive Local Likelihood Distribution Modelmentioning

confidence: 99%

Bayesian Shape Localization for Face Recognition Using Global and Local Textures

Yan

et al. 2004

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

We present a fully automatic system for face recognition in databases with only a small number of samples (even single sample) for each individual. In this paper, the shape localization problem is formulated in the Bayesian framework. In the learning stage, the RankBoost approach is introduced to model the likelihood of local features associated with the fiducial point, while preserving the prior ranking order between the ground truth position and its neighbors; in the inferring stage, a simple efficient iterative algorithm is proposed to uncover the MAP shape by locally modeling the likelihood distribution around each fiducial point. Based on the accurately located fiducial points, two popular mutual enhancing texture features are automatically extracted and integrated for human face representation: global texture features, which are the normalized shape-free gray-level values enclosed in the mean shape, and local texture features, which are represented by the Gabor wavelets extracted at the fiducial points (eye corners and mouth, etc.). Global texture mainly encodes the low-frequency information of a face, while local texture encodes the local high-frequency components. The extensive experiments illustrate that our proposed shape localization approach significantly improved the shape location accuracy, robustness, and face recognition rate; moreover, the experiments conducted on FERET and Yale databases show that our algorithm outperformed the classical eigenfaces, fisherfaces, as well as other approaches utilizing the shape, global, and local textures.

show abstract

Active Shape Models and the shape approximation problem

Cited by 56 publications

References 12 publications

A deformable-model approach to semi-automatic segmentation of CT images demonstrated by application to the spinal canal

A deformable-model approach to semi-automatic segmentation of CT images demonstrated by application to the spinal canal

Facial surface analysis by 3D laser scanning and geometric morphometrics in relation to sexual dimorphism in cerebral–craniofacial morphogenesis and cognitive function

Bayesian Shape Localization for Face Recognition Using Global and Local Textures

Contact Info

Product

Resources

About