Kohonen SOM for Image Slides Sequencing

Abstract : In this paper we present a new approach to sequencing of 2-D slide images with the goal of 3-D object reconstructions. We focus our attention mostly on microscope images obtained from serial sections of biological tissues. For adequate 3-D body reconstruction the correct sequence of section should be available. We propose a modified SOM Kohonen networks with open chain topology for true sequence estimation based on based on 2-D image features invariant to section image translation and rotation, but sensitive to a scale of an object on the slide. We provide an experimental validation of the proposed method using artificial section images of a mechanical device and real microscopic histological section images.
Type de document :
Communication dans un congrès
Khalid Saeed; Władysław Homenda. 15th IFIP International Conference on Computer Information Systems and Industrial Management (CISIM), Sep 2016, Vilnius, Lithuania. Springer International Publishing, Lecture Notes in Computer Science, LNCS-9842, pp.352-365, 2016, Computer Information Systems and Industrial Management. 〈10.1007/978-3-319-45378-1_32〉
Liste complète des métadonnées

Littérature citée [26 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01637466
Contributeur : Hal Ifip <>
Soumis le : vendredi 17 novembre 2017 - 15:43:44
Dernière modification le : samedi 18 novembre 2017 - 01:16:37

Fichier

 Accès restreint
Fichier visible le : 2019-01-01

Connectez-vous pour demander l'accès au fichier

Licence


Distributed under a Creative Commons Paternité 4.0 International License

Identifiants

Collections

Citation

Ewa Skubalska-Rafajłowicz, Aneta Górniak. Kohonen SOM for Image Slides Sequencing. Khalid Saeed; Władysław Homenda. 15th IFIP International Conference on Computer Information Systems and Industrial Management (CISIM), Sep 2016, Vilnius, Lithuania. Springer International Publishing, Lecture Notes in Computer Science, LNCS-9842, pp.352-365, 2016, Computer Information Systems and Industrial Management. 〈10.1007/978-3-319-45378-1_32〉. 〈hal-01637466〉

Partager

Métriques

Consultations de la notice

8