Share Email Print

Proceedings Paper

Information based universal feature extraction
Author(s): Mohammad Amiri; Rüdiger Brause
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In many real world image based pattern recognition tasks, the extraction and usage of task-relevant features are the most crucial part of the diagnosis. In the standard approach, they mostly remain task-specific, although humans who perform such a task always use the same image features, trained in early childhood. It seems that universal feature sets exist, but they are not yet systematically found. In our contribution, we tried to find those universal image feature sets that are valuable for most image related tasks. In our approach, we trained a neural network by natural and non-natural images of objects and background, using a Shannon information-based algorithm and learning constraints. The goal was to extract those features that give the most valuable information for classification of visual objects hand-written digits. This will give a good start and performance increase for all other image learning tasks, implementing a transfer learning approach. As result, in our case we found that we could indeed extract features which are valid in all three kinds of tasks.

Paper Details

Date Published: 14 February 2015
PDF: 6 pages
Proc. SPIE 9445, Seventh International Conference on Machine Vision (ICMV 2014), 94450D (14 February 2015); doi: 10.1117/12.2181001
Show Author Affiliations
Mohammad Amiri, Goethe Univ. (Germany)
Rüdiger Brause, Goethe Univ. (Germany)

Published in SPIE Proceedings Vol. 9445:
Seventh International Conference on Machine Vision (ICMV 2014)
Antanas Verikas; Branislav Vuksanovic; Petia Radeva; Jianhong Zhou, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?