Chapter 10

Statistical Shape Models


This chapter deals with the topic of statistical shape models (SSMs). It is shown how these can be viewed as an extension of the concept of inferential statistics to the domain of shapes rather than univariate or multivariate data. The relationship between SSMs and the field of dimensionality reduction is described. The steps involved in the formation of SSMs are outlined: parameterizing the shape, aligning the centroids, computing the covariance matrix, and computing its eigenvectors and eigenvalues. It is also shown how new shapes can be produced from an SSM. A review of the biomedical applications of SSMs is provided. Finally, the chapter ends with a guided exercise on the formation of an ...

Get Statistics for Biomedical Engineers and Scientists now with the O’Reilly learning platform.

O’Reilly members experience live online training, plus books, videos, and digital content from nearly 200 publishers.