Automatic Biological Cell Counting Using a Modified Gradient Hough Transform

Abstract : We present a computational method for pseudo-circular object detection and quantitative characterization in digital images, using the gradient accumulation matrix as a basic tool. This Gradient Accumulation Transform (GAT) was first introduced in 1992 by Kierkegaard and recently used by Kaytanli & Valentine. In the present article, we modify the approach by using the phase coding studied by Cicconet, and by adding a local contributor list (LCL) as well as a used contributor matrix (UCM), which allow for accurate peak detection and exploitation. These changes help make the GAT algorithm a robust and precise method to automatically detect pseudo-circular objects in a microscopic image. We then present an application of the method to cell counting in microbiological images.
Type de document :
Article dans une revue
Microscopy and Microanalysis, Cambridge University Press (CUP), 2017, 23 (01), pp.11 - 21. 〈10.1017/S1431927616012617〉
Liste complète des métadonnées

https://hal-univ-bourgogne.archives-ouvertes.fr/hal-01509941
Contributeur : Pam - Université de Bourgogne <>
Soumis le : mardi 18 avril 2017 - 17:26:19
Dernière modification le : mercredi 12 septembre 2018 - 01:26:59

Identifiants

Collections

Citation

Emmanuel Denimal, Ambroise Marin, Stéphane Guyot, Ludovic Journaux, Paul Molin. Automatic Biological Cell Counting Using a Modified Gradient Hough Transform. Microscopy and Microanalysis, Cambridge University Press (CUP), 2017, 23 (01), pp.11 - 21. 〈10.1017/S1431927616012617〉. 〈hal-01509941〉

Partager

Métriques

Consultations de la notice

112