TY - JOUR
AU - Angulo, Jesus
PY - 2014/06/14
Y2 - 2024/02/22
TI - STRUCTURE TENSOR IMAGE FILTERING USING RIEMANNIAN L1 AND Lā CENTER-OF-MASS
JF - Image Analysis and Stereology
JA - Image Anal Stereol
VL - 33
IS - 2
SE - Original Research Paper
DO - 10.5566/ias.v33.p95-105
UR - https://www.ias-iss.org/ojs/IAS/article/view/1075
SP - 95-105
AB - Structure tensor images are obtained by a Gaussian smoothing of the dyadic product of gradient image. These images give at each pixel a <em>n</em>Ć<em>n</em> symmetric positive definite matrix SPD(<em>n</em>), representing the local orientation and the edge information. Processing such images requires appropriate algorithms working on the Riemannian manifold on the SPD(<em>n</em>) matrices. This contribution deals with structure tensor image filtering based on <em>L<sup>p</sup></em> geometric averaging. In particular, <em>L</em><sup>1</sup> center-of-mass (Riemannian median or Fermat-Weber point) and <em>L</em><sup>ā</sup> center-of-mass (Riemannian circumcenter) can be obtained for structure tensors using recently proposed algorithms. Our contribution in this paper is to study the interest of <em>L</em><sup>1</sup> and <em>L</em><sup>ā</sup> Riemannian estimators for structure tensor image processing. In particular, we compare both for two image analysis tasks: (i) structure tensor image denoising; (ii) anomaly detection in structure tensor images.
ER -