Skip to Main content Skip to Navigation
Conference papers

Détection de primitives linéaires et circulaires par une approche a contrario

Abstract : Low-level image understanding requires the use of different detectors for basic primitives, such as line segments or circular arcs. Most of the existent detectors deal with problems that have been (and still are) extensively studied like parameter tunning, control of number of false detections or execution time. In this paper, we focus on detecting simultaneously lines and circles in an image, while controlling the number of false detections and without any need of parameter tunning. We present an algorithm which extends the Line Segment Detector (LSD) for circles, both being based on the a contrario approach. Due to the fact that the proposed detector targets two different types of primitives, the a contrario validation is used as a criterion for model selection, which is a novelty in the a contrario-based works. In addition, we propose a new algebraic method for estimating a circle, which benefits equally from the direction of the gradient of the contour points, and not only from their position.
Document type :
Conference papers
Complete list of metadata

Cited literature [21 references]  Display  Hide  Download

https://hal.inria.fr/inria-00595749
Contributor : Peter Sturm Connect in order to contact the contributor
Submitted on : Wednesday, May 25, 2011 - 2:40:06 PM
Last modification on : Wednesday, June 1, 2022 - 4:18:51 AM
Long-term archiving on: : Friday, August 26, 2011 - 2:25:50 AM

File

paper54.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00595749, version 1

Citation

Viorica Pătrăucean, Pierre Gurdjos, Géraldine Morin, Jean Conter. Détection de primitives linéaires et circulaires par une approche a contrario. ORASIS - Congrès des jeunes chercheurs en vision par ordinateur, INRIA Grenoble Rhône-Alpes, Jun 2011, Praz-sur-Arly, France. ⟨inria-00595749⟩

Share

Metrics

Record views

187

Files downloads

431