Abstract
In this chapter we work directly with the offset-normal shape distribution as a probability model for statistical inference on a sample of landmark configurations. This enables inference for induced Gaussian processes from configurations onto the shape space. Following Kume and Welling (J Comput Graph Stat 19:702–723, 2010), an Expectation Maximization (EM) algorithm for computing exact maximum likelihood (ML) estimation of the involved parameters is discussed. The chapter concludes with an application on facial expression analysis.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Adali T, Schreier PJ, Scharf LL (2011) Complex-valued signal processing: the proper way to deal with impropriety. IEEE Trans Signal Process 59(11):5101–5125
Dempster A, Laird N, Rubin D (1977) Maximum likelihood from incomplete data via the em algorithm. J R Stat Soc Ser B 34(1):1–38
Dryden IL, Mardia KV (1991) General shape distributions in the plane. Adv Appl Probab 23:259–276
Dryden IL, Mardia KV (1998) Statistical shape analysis. Wiley, London
Ekman P, Friesen WV (1971) Constants across culture in the face and emotion. J Pers Soc Psychol 17:124–129
Gradshteyn I, Ryzhik I (1980) Table of integrals, series, and products. Academic, New York
Kume A, Welling M (2010) Maximum likelihood estimation for the offset-normal shape distributions using em. J Comput Graph Stat 19:702–723
McLachlan G, Krishnan T (1997) The EM algorithm and extensions. Wiley, New York
Neeser F, Massey J (1993) Proper complex random processes with applications to information theory. IEEE Trans Inf Theory 39(4):1293–1302
Picinbono B (1996) Second-order complex random vectors and normal distributions. IEEE Trans Signal Process 44(10):2637–2640
Schreier P, Scharf L (2003) Second-order analysis of improper complex random vectors and processes. IEEE Trans Signal Process 51(3):714–725
Wallhoff F (2006) Facial expressions and emotion database. http://www.mmk.ei.tum.de/~waf/fgnet/feedtum.html
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2016 The Authors
About this chapter
Cite this chapter
Brombin, C., Salmaso, L., Fontanella, L., Ippoliti, L., Fusilli, C. (2016). Shape Inference and the Offset-Normal Distribution. In: Parametric and Nonparametric Inference for Statistical Dynamic Shape Analysis with Applications. SpringerBriefs in Statistics. Springer, Cham. https://doi.org/10.1007/978-3-319-26311-3_2
Download citation
DOI: https://doi.org/10.1007/978-3-319-26311-3_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-26310-6
Online ISBN: 978-3-319-26311-3
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)