A Generic System for Image Interpretation Using Flexible Templates

Hill,; Cootes,; Taylor, Chris

doi:10.5244/c.6.29

“…the variations in the shapes of the sub-components and the geometric relationships between components. Such a model, representing a section through the ventricles in the brain in MR scans is described by Hill et al in [16].…”

Section: Discussionmentioning

confidence: 99%

“…A local optimiser called the Active Shape Model has been developed [15] which provides a way of iteratively improving an initial estimate of the position, pose and shape parameters of a model fitted to image data. The model has also been used in conjunction with a generate and test strategy based around Genetic Algorithms [16]. The hand and resistor models described above have been successfully used to find examples in images with both techniques.…”

Section: Discussionmentioning

confidence: 99%

Training Models of Shape from Sets of Examples

Cootes¹,

Taylor²,

Cooper³

et al. 1992

Procedings of the British Machine Vision Conference 1992

Self Cite

View full text Add to dashboard Cite

A method for building flexible shape models is presented in which a shape is represented by a set of labelled points. The technique determines the statistics of the points over a collection of example shapes. The mean positions of the points give an average shape and a number of modes of variation are determined describing the main ways in which the example shapes tend to deform from the average. In this way allowed variation in shape can be included in the model. The method produces a compact flexible 'Point Distribution Model' with a small number of linearly independent parameters, which can be used during image search. We demonstrate the application of the Point Distribution Model in describing two classes of shapes.

show abstract

“…The techniques described above have been used successfully in a number of applications, both industrial and medical [8]. Here we show results obtained using the resistor and hand models described in the companion paper [5].…”

Section: Examples Using Active Shape Modelsmentioning

confidence: 92%

Active Shape Models - 'smart snakes'

Cootes¹,

Taylor²

1992

Procedings of the British Machine Vision Conference 1992

Self Cite

View full text Add to dashboard Cite

We describe 'Active Shape Models' which iteratively adapt to refine estimates of the pose, scale and shape of models of image objects. The method uses flexible models derived from sets of training examples. These models, known as Point Distribution Models, represent objects as sets of labelled points. An initial estimate of the location of the model points in an image is improved by attempting to move each point to a better position nearby. Adjustments to the pose variables and shape parameters are calculated. Limits are placed on the shape parameters ensuring that the example can only deform into shapes conforming to global constraints imposed by the training set. An iterative procedure deforms the model example to find the best fit to the image object. Results of applying the method are described. The technique is shown to be a powerful method for refining estimates of object shape and location.

show abstract

“…We intend to produce a better model by including the square solder pads. The method is effective in maintaining the global shape constraints of the model and works well given a sufficiently good starting approximation; we discuss methods of obtaining such initial hypotheses elsewhere [6,7,8].…”

Section: Finding Resistors With An Asmmentioning

confidence: 99%

Active Shape Models — ‘Smart Snakes’

Cootes

¹

,

Taylor

²

1992

Bmvc92

Self Cite

View full text Add to dashboard Cite

We describe 'Active Shape Models' which iteratively adapt to refine estimates of the pose, scale and shape of models of image objects. The method uses flexible models derived from sets of training examples. These models, known as Point Distribution Models, represent objects as sets of labelled points. An initial estimate of the location of the model points in an image is improved by attempting to move each point to a better position nearby. Adjustments to the pose variables and shape parameters are calculated. Limits are placed on the shape parameters ensuring that the example can only deform into shapes conforming to global constraints imposed by the training set. An iterative procedure deforms the model example to find the best fit to the image object. Results of applying the method are described. The technique is shown to be a powerful method for refining estimates of object shape and location.

show abstract

A Generic System for Image Interpretation Using Flexible Templates

Cited by 21 publications

References 3 publications

Training Models of Shape from Sets of Examples

Training Models of Shape from Sets of Examples

Active Shape Models - 'smart snakes'

Active Shape Models — ‘Smart Snakes’

Contact Info

Product

Resources

About