An Evolutionary Approach For Blind Deconvolution Of Barcode Images With Nonuniform Illumination

Laurent Dumas (1) , Mohammed El Rhabi (2) , Gilles Rochefort

1 LMV - Laboratoire de Mathématiques de Versailles
2 IMI - Département Ingénierie Mathématique et Informatique, École des Ponts ParisTech

—This paper deals with a joint nonuniform illumination estimation and blind deconvolution for barcode signals by using evolutionary algorithms. Indeed, such optimization problems are highly non convex and a robust method is needed in case of noisy and/or blurred signals and nonuniform illumination. Here, we present the construction of a genetic algorithm combining discrete and continuous optimization which is successfully applied to decode real images with very strong noise and blur.

Domaines: Mathématiques [math]; Analyse numérique [math.NA]; Mathématiques [math]; Statistiques [math.ST]; Informatique [cs]; Informatique [cs]; Vision par ordinateur et reconnaissance de formes [cs.CV]; Informatique [cs]; Modélisation et simulation; Informatique [cs]; Traitement du signal et de l'image [eess.SP]

Laurent Dumas, Mohammed El Rhabi, Gilles Rochefort. An Evolutionary Approach For Blind Deconvolution Of Barcode Images With Nonuniform Illumination. 2011 IEEE Congress on Evolutionary Computation (CEC), Jun 2011, New Orleans, United States. ⟨10.1109/CEC.2011.5949917⟩. ⟨hal-01812543⟩