Les filtres de Hermite et de Gabor donnent-ils des modèles équivalents du système visuel humain?

Abstract : Receptive field profile models have played an important role in image processing since they efficiently code visual information relevant to human perception. Among the suggested mathematical models, the Gabor model is well known and widely used. A less used known model is the one of Hermite which is based on analysis filters of the Hermite transform created by J.-B. Martens. It agrees with the Gaussian derivative model for human vision developed by Richard A. Young. However, it is not as known as the Gabor one although it has the advantage of an orthogonal basis and a better fit to cortical data. In this paper we present an analytical comparison based on minimization of the energy error between the two models, and so the optimal parameters letting the two models be close to each other are found. The results show that both models are equivalent. As a matter of fact, we can implement a Hermite filter with an equivalent Gabor filter and vice versa, provided that conditions leading to error minimization are held. The results also show that both models extract at least about the same frequency information. We hope to provide a framework in which applications using the Gabor model could be extended to that of Hermite.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01593795
Contributor : Équipe Gestionnaire Des Publications Si Liris <>
Submitted on : Tuesday, September 26, 2017 - 4:46:40 PM
Last modification on : Friday, January 11, 2019 - 4:31:47 PM

Identifiers

  • HAL Id : hal-01593795, version 1

Citation

Carlos Rivero-Moreno, Stéphane Bres. Les filtres de Hermite et de Gabor donnent-ils des modèles équivalents du système visuel humain?. Journées francophones des jeunes chercheurs en vision par ordinateur, ORASIS 2003, May 2003, Gérardmer, France. pp.423-432. ⟨hal-01593795⟩

Share

Metrics

Record views

129