Texture enhanced appearance models

Research output: Contribution to journalArticle

  • External authors:
  • Rasmus Larsen
  • Mikkel B. Stegmann
  • Sune Darkner
  • Søren Forchhammer
  • Bjarne Kjær Ersbøll

Abstract

Statistical region-based registration methods such as the active appearance model (AAM) are used for establishing dense correspondences in images. At low resolution, images correspondences can be recovered reliably in real-time. However, as resolution increases this becomes infeasible due to excessive storage and computational requirements. We propose to reduce the dimensionality of the textural components by selecting a subset of basis functions from a larger dictionary, estimate regression splines and model only the coefficients of the retained basis functions. We demonstrate the use of two types of bases, namely wavelets and wedgelets. The former extends the previous work of Wolstenholme and Taylor where Haar wavelet coefficient subsets were applied. The latter introduces the wedgelet regression tree based on triangulated domains. The wavelet and wedgelet regression splines are functional descriptions of the intensity information and serve to (1) reduce noise and (2) produce a compact textural description. Dimensionality reduction by subsampling in the CDF 9-7 wavelet and wedgelet representations yield better results than 'standard' subsampling in the pixel domain. We show that the bi-orthogonal CDF 9-7 wavelet yields better results than the Haar wavelet. Further, we show that the inherent frequency separation in wavelets allows for cost-free band-pass filtering, e.g. edge-emphasis, and that this edge enhancement provide better results in terms of segmentation accuracy. Wedgelet representation are superior to wavelet representations at high dimensionality-reduction rates. At low reduction rates an edge enhanced wavelet representation provides better segmentation accuracy than the full standard AAM model. © 2006 Elsevier Inc. All rights reserved.

Bibliographical metadata

Original languageEnglish
Pages (from-to)20-30
Number of pages10
JournalComputer Vision and Image Understanding
Volume106
Issue number1
DOIs
Publication statusPublished - Apr 2007