15 May 2003 Automated landmark generation for constructing statistical shape models
Author Affiliations +
In this paper, a novel method is provided for automatic generation of landmarks to construct statistical shape models. The method generates a sparse polygonal approximation for each shape example in the training set and then automatically aligns the shape polygons by minimizing the L2 distance of the turning functions of their polygonal approximations. The turning function measures the angle of counterclockwise tangent as a function of the arc-length and is especially suitable for shape alignment since it is piecewise constant for a polygon, and invariant under translation, rotation and scaling of the polygon. Based on the minimal L2 distance, a shape classifier is used to remove the shapes very different from the training set to prevent undesirable distortion of the mean shape. For some shapes with non-rigid deformation, such as hands, a local alignment is performed by using a visual part decomposition scheme and a partial match algorithm. Finally, a set of salient match pairs are detected and used to generate the landmarks. This method has been successfully applied to various anatomical structures. As expected, a large portion of shape variability is captured.
© (2003) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Hui Luo, "Automated landmark generation for constructing statistical shape models", Proc. SPIE 5032, Medical Imaging 2003: Image Processing, (15 May 2003); doi: 10.1117/12.481124; https://doi.org/10.1117/12.481124


Geometric modeling for computer vision
Proceedings of SPIE (February 01 1992)
Shape and Function
Proceedings of SPIE (March 27 1987)
Bilinear models of natural images
Proceedings of SPIE (February 07 2007)
Shape from texture: an evaluation of visual cues
Proceedings of SPIE (May 01 1994)
Approximation of sweep surfaces by tensor product NURBS
Proceedings of SPIE (February 01 1992)

Back to Top