Computing Reviews
Today's Issue Hot Topics Search Browse Recommended My Account Log In
Review Help
Search
Application in target recognition based on gray system theory and mathematical morphology edge detection
Li H., Jia X., Liu Y., Tan H., Zheng N.  ICCSEE 2012 (Proceedings of the 2012 International Conference on Computer Science and Electronics Engineering, Hangzhou, China, Mar 23-25, 2012)611-614.2012.Type:Proceedings
Date Reviewed: Jul 26 2013

Target recognition (or more broadly, pattern recognition or template matching) has important military, industrial, and scientific applications, including target tracking, missile guidance, aircraft navigation, robotic vision, and digital image processing. The authors of this paper use mathematical morphology and a methodology based on gray system theory to solve target recognition problems.

Traditionally, target recognition includes the following stages:

(1) Forming and storing a template (reference) image of the target pre-flight;
(2) Obtaining the current image in-flight with radar, optical, or other sensors;
(3) Preprocessing the current image to improve its quality, usually by selecting some specific features such as edges or object boundaries;
(4) Calculating a similarity function between the template and the current image (a correlation function is commonly used at this stage); and
(5) Determining the extremum of the similarity function, and making a decision whether the current image is the target and whether there is a space misalignment between the template and the current image.

For preprocessing, the authors use the Laplacian of Gaussian (LoG) operator (one of the most popular operators used in edge detection). For the similarity function, they use the degree of gray incidence, a numerical characteristic for the relationship of closeness between two sequences [1].

Experimental results are presented in the form of aircraft images at different stages of image processing. Visually, the results seem to confirm the effectiveness of the proposed algorithms.

However, the paper lacks quantitative evaluations of the results achieved. There is no comparison of the proposed method with other methods that can be used for the same purpose, so it is unclear whether this method should be implemented and, if so, on which occasions. Although they use gray incidence, the authors refer to it as correlation without identifying the differences between these two notions. The authors indicate that research on this topic has just started and further studies will focus on image compression and predictive values for overflow.

The paper’s intended audience includes academics and practitioners working on target recognition and, more broadly, digital image processing methods. Readers who are interested in this topic can find additional information on the subject [2,3].

Reviewer:  Alexei Botchkarev Review #: CR141403 (1310-0938)
1) Liu, S.; Fang, Z.; Lin, Y. A new definition for the degree of grey incidence. Scientific Inquiry 7, 2(2006), 111–124.
2) Yuan, C.; Liu, S.; Chen, W. Grey incidence analysis of the factors which are linear correlative. In Proc. of the 2010 IEEE International Conference on Systems Man and Cybernetics. IEEE, 2010, 970–976. http://dx.doi.org/10.1109/ICSMC.2010.5641758.
3) Yingying, Z.; Chuanzhe, L. Coordination state of China’s fictitious economy and real economy. In Proc. of the 2010 International Conference on Information Management, Innovation Management and Industrial Engineering. IEEE, 2010, 501–504. http://dx.doi.org/10.1109/ICIII.2010.601.
Bookmark and Share
  Reviewer Selected
 
 
General (I.5.0 )
 
 
Edge And Feature Detection (I.4.6 ... )
 
Would you recommend this review?
yes
no
Other reviews under "General": Date
Recognizing unexpected objects: a proposed approach
Rosenfeld A. (ed) International Journal of Pattern Recognition and Artificial Intelligence 1(1): 71-84, 1987. Type: Article
Jun 1 1988
Pattern recognition: human and mechanical
Watanabe S., John Wiley & Sons, Inc., New York, NY, 1985. Type: Book (9789780471808152)
Mar 1 1986
Perceptrons: expanded edition
Minsky M., Papert S., MIT Press, Cambridge, MA, 1988. Type: Book (9789780262631112)
Apr 1 1990
more...

E-Mail This Printer-Friendly
Send Your Comments
Contact Us
Reproduction in whole or in part without permission is prohibited.   Copyright 1999-2024 ThinkLoud®
Terms of Use
| Privacy Policy