An Articulating Statistical Shape Model of the Human Hand

Houtte, Jeroen Van; Stanković, Kristina; Booth, Brian G.; Danckaers, Femke; Bertrand, Véronique; Verstreken, Frederik; Sijbers, Jan; Huysmans, Toon

doi:10.1007/978-3-319-94223-0_41

Cited by 4 publications

(2 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The compactness is often used in statistical models to quantify the efficiency of the model in describing the total variance in the population [12]. The compactness ability can be measured as the cumulated variance, and is defined as:…”

Section: Selection Of Construction Methodsmentioning

confidence: 99%

“…The enlarged contact areas contributed to a better grip as well as reduced possibilities of being affected by cumulative trauma disorders. A statistical shape model (SSM) of the human hand, which can represent the 3D hand shape with a limited number of parameters with a certain accuracy, can be utilized as a high-fidelity digital representation of the hand in many applications [12]. However, the human hand has complicated structures.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Posture-Invariant Three Dimensional Human Hand Statistical Shape Model

Yang

Yuan

Huysmans

et al. 2021

Journal of Computing and Information Science in Engineering

Self Cite

View full text Add to dashboard Cite

A high-fidelity digital representation of the human body is a key enabler for integrating humans in a digital twin. Among different parts of human body, building the model of the hand can be a challenging task due to the posture deviations among collected scans. In this paper, we proposed a posture invariant hand statistical shape model (SSM) based on 59 3D scans of human hands. First, the 3D scans were spatially aligned using a Möbius sphere-based algorithm. An articulated skeleton, which contains 20 bone segments and 16 joints, was embedded for each 3D scan. Then all scans were aligned to the same posture using the skeleton and the linear blend skinning algorithm. Three methods, i.e. Principal Component Analysis (PCA), kernel-PCA with different kernel functions, and Independent Component Analysis, were evaluated in the construction of the SSMs regarding the compactness, the generalization ability and the specificity. The PCA-based SSM was selected, where 20 principal components were used as parameters for the model. Results of the leave-one-out validation indicate that the proposed model was able to fit a given 3D scan of the human hand at an accuracy of 1.21 ± 0.14 mm. Experiment results also indicated that the proposed SSM outperforms the SSM that was built on the scans without posture correction. It is concluded that the proposed posture correction approach can effectively improve the accuracy of the hand SSM, therefore enables its wide usage in human integrated digital twin applications.

show abstract

Section: Selection Of Construction Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%