Posture-invariant statistical shape analysis using Laplace operator

Statistical shape analysis is a tool that allows to quantify the shape variability of a population of shapes. Traditional tools to perform statistical shape analysis compute variations that reflect both shape and posture changes simultaneously. In many applications, such as ergonomic design applications, we are only interested in shape variations. With traditional tools, it is not straightforward to separate shape and posture variations. To overcome this problem, we propose an approach to perform statistical shape analysis in a posture-invariant way. The approach is based on a local representation that is obtained using the Laplace operator.

Graphical abstractFigure optionsDownload full-size imageDownload high-quality image (468 K)Download as PowerPoint slideHighlights► We propose an approach to perform posture-invariant statistical shape analysis. ► The approach is based on a local representation obtained with the Laplace operator. ► Our approach yields a better statistical model than standard principal component analysis.