The Gradient Product Transform: An Image Filter for Symmetry Detection
Christoph Dalitz, Jens Wilberg, Manuel Jeltsch
→ BibTeX
@article{ipol.2019.270,
    title   = {{The Gradient Product Transform: An Image Filter for Symmetry Detection}},
    author  = {Dalitz, Christoph and Wilberg, Jens and Jeltsch, Manuel},
    journal = {{Image Processing On Line}},
    volume  = {9},
    pages   = {413--431},
    year    = {2019},
    doi     = {10.5201/ipol.2019.270},
}
% if your bibliography style doesn't support doi fields:
    note    = {\url{https://doi.org/10.5201/ipol.2019.270}}
published
2019-12-09
reference
Christoph Dalitz, Jens Wilberg, and Manuel Jeltsch, The Gradient Product Transform: An Image Filter for Symmetry Detection, Image Processing On Line, 9 (2019), pp. 413–431. https://doi.org/10.5201/ipol.2019.270

Communicated by Julie Delon
Demo edited by Mariano Rodríguez

Abstract

The Gradient Product Transform (GPT) is an image filter that converts a grayscale image into a float image, such that points representing a point reflection symmetry center obtain a high score. Beside the symmetry score, it also yields an estimator for the size of the symmetry region around each point. Apart from describing the GPT, the article also explains its application for two use cases: detection of objects with a point reflection or C2m rotational symmetry, and the extraction of blood vessel skeletons from medical images. For the detection of symmetric objects, a score normalization procedure is suggested that allows to choose a fixed threshold for score values representing actual symmetries.

Download