Home
Call For Papers
Submission
Author
Registration
Publications
About
Contact Us

  A Comparative Study on Target Detection in Military Field Using Various Digital Image Processing Techniques  
  Authors : Arya Raj A.K; Radhakrishnan B
  Cite as:

 

Automatic aerial image interpretation is one of the new rising high-tech application fields, and it’s proverbially applied in the military domain. This survey paper compares a different approach for target detection and classification of objects by texture clustering and structure features extraction. By clustering the texture feature effective image segmentation is achieved and thus obtain the structure features of target objects. Typical man-made objects including airplanes, tank, ships, mines and vehicles in complex natural background can be detected.

 

Published In : IJCSN Journal Volume 5, Issue 1

Date of Publication : February 2016

Pages : 181-185

Figures :03

Tables : --

Publication Link : A Comparative Study on Target Detection in Military Field Using Various Digital Image Processing Techniques

 

 

 

Arya Raj A.K : received her B.Tech (Computer Science & Engineering) degree from Cochin University of Science & Technology in 2008. She worked at College of Engineering Trivandrum as Lecturer. She is currently pursuing her M.Tech Degree in Computer Science & Engineering from University of Kerala.

Radhakrishnan B : is currently working as Asst. Professor in Computer Science & Engineering department. He has more than 14 years experience in teaching and has published papers on data mining and image processing. His research interests include image processing, data mining, image mining

 

 

 

 

 

 

 

Target Detection

DCT

Morphological Enhancing Texture Clustering

Segmentation

Structure Feature Extraction

This survey paper proposes an approach for detecting targets in the military field. Target objects are detected by clustering the texture feature and then extracting the geometric structure features. During the texture feature extraction process, we compare the segmentation result of histogram-based and Tamura-based texture features. FCM is chosen as the clustering algorithm. From the study of different segmentation methods we prefer Markov Random Field method because accurate segmentation was achieved on seabed types where other models failed. For geometric structure feature extraction edges of the target objects are detected. Canny and Tupin edge detection method is compared and from this survey Tupin is considered better than Canny.

 

 

 

 

 

 

 

 

 

[1] Fei Cai, Honghui Chen, Jianwei Ma, “ Man-made Object Detection Based on Texture Clustering and Geometric Structure Feature Extracting”, I.J. Information Technology and Computer Science, 2011, Volume 2, pp.9-16. [2] Guo-Jia Hou, Xin Luan, Da-Lei Song, Xue-Yan Ma, “Underwater Man-Made Object Recognition on the Basis of Color and Shape Features”, Coastal Education and Research Foundation, September 2015. [3] Michael Teutsch, “Segmentation and Classification of Man-Made Maritime Objects in Terrasar-X images”, Geoscience and Remote Sensing Symposium (IGARSS), 2011 IEEE International, pp.2657-2660. [4] Poh Bee Tong, Chin Swee Chia, “Automatic Detection and Classification of Man-made Targets in Side Scan Sonar Images”, Maritime Technology and Research, 2011 IEEE International [5] Fazal Malik and Baharum Baharudin, “The Statistical Quantized Histogram Texture Features Analysis for Image Retrieval Based on Median and Laplacian Filters in the DCT Domain”, The International Arab Journal of Information Technology, November 2013, Vol. 10, No. 6. [6] K.Sreedhar and B.Panlal, “Enhancement of images using Morphological Transformations”, International Journal of Computer Science & Information Technology (IJCSIT), Feb 2012, Vol.4, pp. 33-50. [7] Alphonsa Thomas and Sreekumar K, “A Survey on Image Feature Descriptors-Color,Shape and Texture”, International Journal of Computer Science and Information Technologies(IJCSIT), 2014, Vol. 5 (6) , pp.7847-7850. [8] Andrzej Materka and Michal Strzelecki, “Texture Analysis Methods – A Review”, National Laboratory of Pattern Recognition (NLPR), 2002, Vol 35, 735–747. [9] Fei Cai, Honghui Chen, Jianwei Ma, “Man-made Object Detection Based on Texture Visual Perception”, I.J. Engineering and Manufacturing, 2012, Vol 3, pp.1-8. [10] Neelima Bagri1 and Punit Kumar Johari, “ A Comparative Study on Feature Extraction using Texture and Shape for Content Based Image Retrieval”, International Journal of Advanced Science and Technology, 2015, Vol.80, pp.41-52. [11] Dr.S.N.Geethalakshmi, Dr.P.Subashini, Mrs.P.Geetha, “A study on detecting and classifying underwater mine like objects using image processing techniques”, International Journal on Computer Science and Engineering (IJCSE), October 2011, Vol. 3, No. 10. [12] Ch.Kavitha, M.Babu Rao, Dr. B.Prabhakara Rao, Dr. A.Govardhan, “Image Retrieval based on Local Histogram and Texture Features”, International Journal of Computer Science and Information Technologies (IJCSIT), 2011, Vol. 2 (2) , pp. 741-746. [13] A.Srinagesh, K.Aravinda, G.P.Saradhi Varma, A.Govardhan, M. SreeLatha, “A Modified Shape Feature Extraction Technique For Image Retrieval”, International Journal of Emerging Science and Engineering (IJESE), June 2013, Volume-1, pp. 2319–6378.