Book contents
- Frontmatter
- Dedication
- Contents
- Preface
- Nomenclature
- 1 Overview of biomedical image analysis
- Part I Signals and systems, image formation, and image modality
- Part II Stochastic models
- Part III Computational geometry
- Part IV Variational approaches and level sets
- Part V Image analysis tools
- 11 Segmentation: statistical approach
- 12 Segmentation: variational approach
- 13 Basics of registration
- 14 Variational methods for shape registration
- 15 Statistical models of shape and appearance
- Index
- References
15 - Statistical models of shape and appearance
from Part V - Image analysis tools
Published online by Cambridge University Press: 05 November 2014
Book contents
- Frontmatter
- Dedication
- Contents
- Preface
- Nomenclature
- 1 Overview of biomedical image analysis
- Part I Signals and systems, image formation, and image modality
- Part II Stochastic models
- Part III Computational geometry
- Part IV Variational approaches and level sets
- Part V Image analysis tools
- 11 Segmentation: statistical approach
- 12 Segmentation: variational approach
- 13 Basics of registration
- 14 Variational methods for shape registration
- 15 Statistical models of shape and appearance
- Index
- References
Summary
Introduction
In this chapter, statistical models, derived from the shape and texture of an object in an image or volume, are studied. Statistical shape and appearance models can capture patterns of variability in shape and gray-level appearance. They form the basis of two of the most powerful tools for object analysis – active shape models (ASM) and active appearance models (AAM) – and are very popular in the computer vision and biomedical imaging analysis literature. This chapter reviews the basic foundation of these two statistical models and provides illustrative examples of their effectiveness in object modeling. The chapter builds upon various ideas studied in previous chapters.
Statistical shape models
The shape of an object can be represented by a set of n points, which can be in any dimension (i.e., 2D or 3D). Adopting Kendall’s definition [15.1][15.2], shape is formally defined as:
DEFINITION 15.1 A shape embodies all the geometrical information that remains when location, scale, and rotational effects are filtered out from an object. ■
- Type
- Chapter
- Information
- Biomedical Image AnalysisStatistical and Variational Methods, pp. 417 - 457Publisher: Cambridge University PressPrint publication year: 2014
References
, Shape manifolds, Procrustean metrics, and complex projective spaces. Bull. Lond. Math. Soc. 16 (2) (1984) 81–121.
, Procrustes methods in the statistical analysis of shape. J. Roy. Stat. Soc. 53(2) (1991) 285–339.Google Scholar
, An introduction to active shape models. In and , eds. Model-Based Methods in Analysis of Biomedical Images, Chapter 7, Oxford University Press (2000) 223–248.Google Scholar
and , Statistical models of appearance for computer vision. Tech. Report, Imaging Science and Biomedical Engineering, University of Manchester, UK (2004).
, Principal warps: thin-plate splines and the decomposition of deformations. IEEE Trans. Pattern Anal. Mach. Intel. 2 (6) (1989) 567–585.CrossRefGoogle Scholar
and , Eigenfaces for recognition. J. Cogn. Neurosci. 3 (1): (1991) 71–86.CrossRefGoogle ScholarPubMed
and , Locating facial features with an extended active shape model. Proc. Eur. Conf. Computer Vision (ECCV) (2008) Berlin: Springer, 504–513.Google Scholar
and , Active appearance models revisited. Int. J. Comp. Vis. 60(2) (2004) 135–164.CrossRefGoogle Scholar
Face Recognition Grand Challenge (FRGC) Database:
and , A global-to-local 2D shape registration in implicit spaces using level sets. Proc. IEEE Int. Conf. Image Processing (ICIP’07), St. Antonio, Texas, September 16–19 (2007) VI-237–VI-240.
, Variational methods for shape and image registrations. Unpublished PhD dissertation, Computer Vision and Image Processing Laboratory, University of Louisville (2008).
, , et al., A new segmentation and registration approach for vertebral body analysis. Proc. 2011 IEEE Int. Symp. Biomedical Imaging (ISBI), March (2011) 2006–2009.CrossRefGoogle Scholar
, Probabilistic and geometric shape based segmentation methods. Unpublished PhD dissertation, Computer Vision and Image Processing Laboratory, University of Louisville (2012).
, , et al., Small pulmonary nodules: reproducibility of three-dimensional volumetric measurement and estimation of time to follow-up. Radiology 231 (2004) 446–452.CrossRefGoogle Scholar
The United States Department of Health and Human Services (NIH):
, , et al., Lung image database consortium: developing a resource for the medical imaging research community. Radiology, 232 (3) (2004) 739–748. (LIDC)CrossRefGoogle ScholarPubMed
, , , and , Parametric and non-parametric nodule models: design and evaluation, Proc. Third Int. Workshop Pulmonary Image Processing in conjunction with MICCAI (2010) 151–162.Google Scholar
, , et al., An AAM-based detection approach of lung nodules from LDCT scans. Int. Symp. Biomedical Imaging (ISBI-12), Barcelona, Spain, May 1–3 (2012) 1040–1043Google Scholar
, Modeling small objects under uncertainties: novel algorithms and applications. Unpublished PhD dissertation, Computer Vision and Image Processing Laboratory, University of Louisville (2012).
, , et al., Automated detection of pulmonary nodules in helical CT images based on an improved template matching technique, IEEE Trans. Med. Imaging 20 (2001) 595–604.Google ScholarPubMed
, , and , A 3-D reconstruction system for the human jaw using a sequence of optical images, IEEE Trans. Med. Imaging 19 (5) (2000) 538–547.CrossRefGoogle ScholarPubMed
, , and , Towards efficient and compact phenomenological representation of arbitrary bidirectional surface reflectance. In Proc. British Machine Vision Conf. (BMVC), BMVA Press (2011) 89.1–89.11.Google Scholar
, , et al., Characterization of dentin and enamel by use of optical coherence tomography. Appl. Opt. 38(10) (1999) 2092–2096.CrossRefGoogle ScholarPubMed
, , et al., Model-based human teeth shape recovery from a single optical image with unknown illumination. In MICCAI Medical Computer Vision Workshop (MCV), (2012), Berlin: Springer, 263–272.Google Scholar
, Phenomenological modeling of image irradiance for non-lambertian surfaces under natural illumination. PhD dissertation, Computer Vision and Image Processing Laboratory, University of Louisville, December, (2012).
and , 3D morphable face models revisited. Proc. IEEE Computer Society Conf. Computer Vision and Pattern Recognition, Miami, FL, 20–25 June (2009) 1327–1334.
and , Color constancy, intrinsic images, and shape estimation. In 12th Eur. Conf. Computer Vision, Florence, Italy, October 7–13 (2012) 57–70.
and , Lambertian reflectance and linear subspaces. IEEE Trans. Pattern Anal. Mach. Intel., 25(2) (2003) 218–233.CrossRefGoogle Scholar
, , , and , Model-based shape recovery from single images of general and unknown lighting. In 16th IEEE Int. Conf. Image Processing (ICIP2009), 7–10 Nov. (2009) 517–520.
, , and , 3D face recovery from intensities of general and unknown lighting using partial least squares. In Proc. 17th IEEE Int. Conf. Image Processing (ICIP2010), Sept. (2010) 4041–4044.
and , Relating intensities with three-dimensional facial shape using partial least squares. Computer Vision, IET, 3 (2009) 60–73.CrossRefGoogle Scholar
and , Shape from shading under various imaging conditions. In Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’07), Minneapolis, MN, June 18–23 (2007) X1–X8.Google Scholar