Using partial stages of Radon transform to detect non straight edges (Conference Presentation)

  1. Oliva-García, Ricardo
  2. Martin-Hernandez, Javier
  3. Gomez-Cardenes, Oscar
  4. Marichal-Hernandez, José Gil 1
  5. Hernández Delgado, Ángela
  1. 1 Universidad de La Laguna
    info

    Universidad de La Laguna

    San Cristobal de La Laguna, España

    ROR https://ror.org/01r9z8p25

Actes de conférence:
Pattern Recognition and Tracking XXXI

ISBN: 9781510635777

Année de publication: 2020

Type: Communication dans un congrès

DOI: 10.1117/12.2557265 GOOGLE SCHOLAR

Résumé

Radon transform, and more specifically the multiscale Discrete Radon Transform, is a valuable tool to find straight structures on images. But the straight lines that DRT finds are those traversing completely the image, and hence DRT is unable to detect non-straight structures. That limitation is normally adressed by evaluating Radon transform on non-overlapped subsquares of the image. In this work we will show that the initial partial transform stages of multiscale DRT contain enough information to detect non-straight edges. By stopping on initial stages of an already linearithmic transform that can be executed on integer arithmethics, the proposed method is found to be much faster than its alternatives. We will show its ability to process images at video acquisition rate on mobile phones