By Topic

Notice of Retraction
Feature extraction and selection for landmine detection using textures of Time-Frequency Representation

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

4 Author(s)
Xiang Gao ; College of Information Science & Engineering, Ocean University of China, Qingdao, China, 266100 ; Guangrong Ji ; Chunhe Wang ; Guangyu Ji

Notice of Retraction

After careful and considered review of the content of this paper by a duly constituted expert committee, this paper has been found to be in violation of IEEE's Publication Principles.

We hereby retract the content of this paper. Reasonable effort should be made to remove all past references to this paper.

The presenting author of this paper has the option to appeal this decision by contacting

Ground Penetrating Radar (GPR) is widely used in the probe of subsurface targets, in which the Time-Frequency Representation (TFR) approaches have been proved effective for GPR signatures. Since we can treat TFR results as 2-D images, texture analysis is an applicable way for image discrimination. In this study, we propose a target detection method based on TFR textures of GPR A-scans and then select 20 descriptors to interpret TFR image into texture features for decision. The mutual correlation and discrimination ability of the descriptors are studied based on the comparative experiment. According to the results, it is clear that the twenty descriptors are redundant and can be grouped into three weak-correlated classes: 11 descriptors of the first class and 2 of the second one are helpful and recommended to use in texture discrimination while the rest can be discarded.

Published in:

Computer Science and Information Technology (ICCSIT), 2010 3rd IEEE International Conference on  (Volume:1 )

Date of Conference:

9-11 July 2010