Information based universal feature extraction

Mohammad Amiri; Rüdiger Brause

doi:10.1117/12.2181001

14 February 2015 Information based universal feature extraction

Mohammad Amiri, Rüdiger Brause

Proceedings Volume 9445, Seventh International Conference on Machine Vision (ICMV 2014); 94450D (2015) https://doi.org/10.1117/12.2181001
Event: Seventh International Conference on Machine Vision (ICMV 2014), 2014, Milan, Italy

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.

Citation Download Citation

Mohammad Amiri and Rüdiger Brause "Information based universal feature extraction", Proc. SPIE 9445, Seventh International Conference on Machine Vision (ICMV 2014), 94450D (14 February 2015); https://doi.org/10.1117/12.2181001

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available