Go to page
 

Bibliographic Metadata

Title
Fisher encoding of convolutional neural network features for endoscopic image classification
AuthorWimmer Andreas Uhl, Georg ; Vécsei, Andreas ; Häfner, Michael ; Uhl, Andreas
Published in
Journal of Medical Imaging, Bellingham, 2018, Vol. 5, Issue 3, 034504-1-034504-11
PublishedBellingham : SPIE, 2018
LanguageEnglish
Document typeJournal Article
Keywords (EN)Databases / Endoscopy / Image classification / Computer programming / Convolutional neural networks / Feature extraction / Image filtering
ISSN2329-4310
URNurn:nbn:at:at-ubs:3-10587 Persistent Identifier (URN)
DOI10.1117/1.JMI.5.3.034504 
Restriction-Information
 The work is publicly available
Files
Fisher encoding of convolutional neural network features for endoscopic image classification [1.13 mb]
Links
Reference
Classification
Abstract (English)

We propose an approach for the automated diagnosis of celiac disease (CD) and colonic polyps (CP) based on applying Fisher encoding to the activations of convolutional layers. In our experiments, three different convolutional neural network (CNN) architectures (AlexNet, VGG-f, and VGG-16) are applied to three endoscopic image databases (one CD database and two CP databases). For each network architecture, we perform experiments using a version of the net that is pretrained on the ImageNet database, as well as a version of the net that is trained on a specific endoscopic image database. The Fisher representations of convolutional layer activations are classified using support vector machines. Additionally, experiments are performed by concatenating the Fisher representations of several layers to combine the information of these layers. We will show that our proposed CNN-Fisher approach clearly outperforms other CNN- and non-CNN-based approaches and that our approach requires no training on the target dataset, which results in substantial time savings compared with other CNN-based approaches.

Stats
The PDF-Document has been downloaded 5 times.