TU Darmstadt / ULB / TUbiblio

Automatic Corneal Tissue Classification Using Bag-Of-Visual-Words Approaches

Bartschat, Andreas and Toso, Lorenzo and Stegmaier, Johannes and Kuijper, Arjan and Mikut, Ralf and Köhler, Bernd and Allgeier, Stephan (2016):
Automatic Corneal Tissue Classification Using Bag-Of-Visual-Words Approaches.
KIT Scientific Publishing, Karlsruhe, In: Forum Bildverarbeitung 2016, Karlsruhe, 01.-02. Dezember 2016, [Conference or Workshop Item]

Abstract

Corneal confocal microscopy is a promising diagnostic method for peripheral neuropathy. It allows the recording of the sub-basal nerve plexus (SNP) and enables the morphological analysis of peripheral nerves. This work evaluates classification models for real-time evaluation of cornea images in order to find suitable methods for an automatic focus adaptation to the SNP. The analyzed Bag-of-Visual-Words method leads to models with an accuracy of 0.9, even on a small training dataset, and a runtime of 18 ms per image. Furthermore, the analysis of the support vector machine real-valued output shows high potential for the implementation of real-time focus optimization methods.

Item Type: Conference or Workshop Item
Erschienen: 2016
Creators: Bartschat, Andreas and Toso, Lorenzo and Stegmaier, Johannes and Kuijper, Arjan and Mikut, Ralf and Köhler, Bernd and Allgeier, Stephan
Title: Automatic Corneal Tissue Classification Using Bag-Of-Visual-Words Approaches
Language: English
Abstract:

Corneal confocal microscopy is a promising diagnostic method for peripheral neuropathy. It allows the recording of the sub-basal nerve plexus (SNP) and enables the morphological analysis of peripheral nerves. This work evaluates classification models for real-time evaluation of cornea images in order to find suitable methods for an automatic focus adaptation to the SNP. The analyzed Bag-of-Visual-Words method leads to models with an accuracy of 0.9, even on a small training dataset, and a runtime of 18 ms per image. Furthermore, the analysis of the support vector machine real-valued output shows high potential for the implementation of real-time focus optimization methods.

Publisher: KIT Scientific Publishing, Karlsruhe
Uncontrolled Keywords: Guiding Theme: Individual Health, Research Area: Computer vision (CV), Image classification, Image processing
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Mathematical and Applied Visual Computing
Event Title: Forum Bildverarbeitung 2016
Event Location: Karlsruhe
Event Dates: 01.-02. Dezember 2016
Date Deposited: 08 May 2019 06:31
Export:
Suche nach Titel in: TUfind oder in Google

Optionen (nur für Redakteure)

View Item View Item