A color object recognition scheme: application to cellular sorting |
| |
Authors: | O Lezoray A Elmoataz H Cardot |
| |
Affiliation: | (1) Laboratoire Universitaire des Sciences Appliquées de Cherbourg (LUSAC) IUT, Site Universitaire de Bellevue, 120 Rue de l'exode, 50000 Saint-Lo, France , FR;(2) Groupe de REcherches en Informatique, Image et Instrumentation de Caen (GREYC) Equipe Image, ISMRA, 6 Bd. du Maréchal Juin, 14050 Caen cedex, France , FR |
| |
Abstract: | This paper presents a color object recognition scheme which proceeds in three sequential steps: segmentation, features extraction
and classification. We mainly focus on the first and the third steps here. A color watershed using global and local criteria
is first described. A color contrast value is defined to select the best color space for segmenting color objects. Then, an
architecture of binary neural networks is described. Its properties relies on the simplification of the recognition problem,
leading to a noticeable increase in the classification rate. We conclude with the abilities of such a recognition scheme and
present an automated cell sorting system.
Received: 15 June 2001 / Accepted: 1 July 2002 Published online: 23 April 2003
Correspondence to: O. Lezoray
(e-mail: Olivier.Lezoray@info.unicaen.fr) |
| |
Keywords: | : Morphology - Color - Segmentation - Classification - Microscopy |
本文献已被 SpringerLink 等数据库收录! |
|