Target Detection of Sar Image using Modified Markov Random Fields Ayed Model Segmentation Along With Google Net Classification
A.Glory Sujitha1, P.Vasuki2, S. Md. Mansoor Roomi3
1A.Glory Sujitha , Research Scholar, Department of CSE, SSM Institute of Engineering and Technology Dindigul, India.
2DR.P.Vasuki , Professor, Department of ECE, KLN College of Information Technology, Pottapalayam Sivagangai District, India
3Dr. S. Md. Mansoor Roomi ,Associate Professor, ECE department, Thiagarajar College of Engineering, District, India.
Manuscript received on November 11, 2019. | Revised Manuscript received on November 20 2019. | Manuscript published on 30 November, 2019. | PP: 11123-11128 | Volume-8 Issue-4, November 2019. | Retrieval Number: D9442118419/2019©BEIESP | DOI: 10.35940/ijrte.D9442.118419
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In the modern world the mechanism of target detection in the SAR images have huge assistance for humans to deal with complex visual signals of satellite images effectively. However, the ultimate aim of the paper was to segment the region of interest precisely from despeckling SAR images. This paper proposes a novel modified Markov random fields ayed model segmentation along with Google NET classification target detection. In the initial stage, the image gets despeckled for removing the unwanted noise. The boundaries of the images were calculated for checking the discontinuity using the canny edge detector. Then in the data reduction step by grouping the similar data items. Then the target region was segmented using the modified Markov random fields ayed model methods then the segmented output can undergo the classification process by using the Google NET CNN architecture. The proposed technique was capable of getting better results under risky conditions . Thus, the results validate the target detection of detection rate in different complexity over the existing methodology Keywords:
Keywords: Despecking SAR Image, Synthetic Aperture Radar (SAR), Canny Edge Detector, Modified Markov Random Fields Ayed Model, Google NET CNN Classification, and Target Detection.
Scope of the Article: Classification.