# Edge Detection Algorithm of a Symmetric Difference Kernel SAR Image Based on the GAN Network Model

^{1}

^{2}

^{3}

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Edge Detection Algorithm of a Symmetric Difference Kernel Sar Image Based on the Gan Network Model

#### 2.1. GAN Network Model

#### 2.2. Multi View Data Generation of Symmetric Difference Kernel SAR Images Based on the GAN Network Model

#### 2.3. Edge Detection of Symmetric Difference Kernel SAR Images

#### 2.3.1. Initial Edge

#### 2.3.2. Edge Post Processing

#### 2.3.3. Calculation of Edge Direction by Hough Transform

## 3. Experimental Analysis

#### 3.1. Classification Effect Analysis of Multi View Data for Symmetric Difference Kernel SAR Images

#### 3.2. Edge Detection Based on Symmetric Difference Kernel SAR Simulation

## 4. Discussion

## 5. Conclusions

## Author Contributions

## Acknowledgments

## Conflicts of Interest

## References

- Li, F.; Fang, F.; Zhang, G. Unsupervised change detection in SAR images using curvelet and L1-norm based soft segmentation. Int. J. Remote Sens.
**2016**, 37, 3232–3254. [Google Scholar] [CrossRef] - Yan, W.; Shi, S.; Pan, L. Unsupervised change detection in SAR images based on frequency difference and a modified fuzzy c-means clustering. Int. J. Remote Sens.
**2018**, 39, 3055–3075. [Google Scholar] [CrossRef] - Wang, X.; Jia, Z.; Yang, J. Change detection in SAR images based on the logarithmic transformation and total variation denoising method. Remote Sens. Lett.
**2017**, 8, 214–223. [Google Scholar] [CrossRef] - Quan, S.; Xiong, B.; Yang, L. Evaluation of different SAR change detectors based on vehicle recognition with MSTAR data set. Remote Sens. Lett.
**2015**, 6, 539–547. [Google Scholar] [CrossRef] - Furse, C.M.; Chen, J.Y.; Gandhi, O.P. The use of the frequency-dependent finite-difference time-domain method for induced current and SAR calculations for a heterogeneous model of the human body. IEEE Trans. Electromagn. Compat.
**2015**, 36, 128–133. [Google Scholar] [CrossRef] - Zhuang, H.; Deng, K.; Fan, H. A novel approach based on structural information for change detection in SAR images. Int. J. Remote Sens.
**2018**, 39, 2341–2365. [Google Scholar] [CrossRef] - Hoekman, D.H.; Reiche, J. Multi-model radiometric slope correction of SAR images of complex terrain using a two-stage semi-empirical approach. Remote Sens. Environ.
**2015**, 156, 1–10. [Google Scholar] [CrossRef] - Jia, M.; Wang, L. Novel class-relativity non-local means with principal component analysis for multitemporal SAR image change detection. Int. J. Remote Sens.
**2018**, 39, 1068–1091. [Google Scholar] [CrossRef] - Verma, O.P.; Parihar, A.S. An optimal fuzzy system for edge detection in color images using bacterial foraging algorithm. IEEE Trans. Fuzzy Syst.
**2017**, 25, 114–127. [Google Scholar] [CrossRef] - Saheba, S.M.; Upadhyaya, T.K.; Sharma R, K. Lunar surface crater topology generation using adaptive edge detection algorithm. IET Image Process.
**2016**, 10, 657–661. [Google Scholar] [CrossRef] - Leng, X.; Ji, K.; Xing, X.; Zou, H.; Zhou, S. Hybrid bilateral filtering algorithm based on edge detection. IET Image Process.
**2017**, 10, 809–816. [Google Scholar] [CrossRef] - González-Hidalgo, M.; Massanet, S.; Mir, A. On the choice of the pair conjunction–implication into the fuzzy morphological edge detector. IEEE Trans. Fuzzy Syst.
**2015**, 23, 872–884. [Google Scholar] [CrossRef] - Alshayeji, M.; Alroomi, S.A.; Abed, S. Optic disc detection in retinal fundus images using gravitational law-based edge detection. Med. Boil. Eng. Comput.
**2016**, 55, 1–14. [Google Scholar] [CrossRef] [PubMed] - Cai, J.; Huang, P.; Chen, L. An efficient circle detector not relying on edge detection. Adv. Space Res.
**2016**, 57, 2359–2375. [Google Scholar] [CrossRef] - Zheng, Y.; Zhou, Y.; Zhou, H. Ultrasound image edge detection based on a novel multiplicative gradient and Canny operator. Ultrason. Imaging
**2015**, 37, 238–250. [Google Scholar] [CrossRef] [PubMed] - Salehi, M.; Namdari, F. Fault classification and faulted phase selection for transmission line using morphological edge detection filter. IET Gener. Transm. Distrib.
**2018**, 12, 1595–1605. [Google Scholar] [CrossRef] - Veni, S.H.K.; Suresh, L.P. An analysis of various edge detection techniques on illuminant variant images. Anaesthesia
**2015**, 61, 617. [Google Scholar] - Sun, Q.; Liang, F.; Wang, F. Investigation on the geometrical characteristics of secondary arc by image edge detection. IEEE Trans. Plasma Sci.
**2018**, 46, 2016–2025. [Google Scholar] [CrossRef] - Gao, W.; Wang, W.F. The fifth geometric-arithmetic index of bridge graph and carbon nanocones. J. Differ. Equ. Appl.
**2017**, 23, 100–109. [Google Scholar] [CrossRef] - Dayal, A. Improving adaptive frameless rendering. Int. J. Comput. Appl.
**2018**, 40, 110–120. [Google Scholar] [CrossRef] - Huang, A.D.; Zhong, Z.; Wu, W. An artificial neural network-based electrothermal model for gan hemts with dynamic trapping effects consideration. IEEE Trans. Microw. Theory Tech.
**2016**, 64, 2519–2528. [Google Scholar] [CrossRef] - Zhang, Y.Q.; Tang, J.L. Clustering sorting algorithm based on digital channelized receiver. J. China Acad. Electron. Inf. Technol.
**2017**, 12, 143–148. [Google Scholar] - Hirano, M.; Tsuzuki, N.; Ikeda, S.; Kobayashi, R. Logdrive: A proactive data collection and analysis framework for time-traveling forensic investigation in IaaS cloud environments. J. Cloud Comput.
**2018**, 7, 18. [Google Scholar] [CrossRef] - Wu, J.; Zhang, C.H.; Wang, R. Harmonic detection algorithm based on third-order generalized-integrator. J. Power Supply
**2018**, 16, 131–136. [Google Scholar] - Zhang, J.; Gao, A.T.; Han, Y.S. A health prognostic algorithm for Li-ion battery based on particle filter. Chin. J. Power Sources
**2015**, 39, 1377–1380. [Google Scholar] - Liu, E.; Jing, X.J. PD algorithm based on two self-balancing vehicle upright control. Autom. Instrum.
**2015**, 1, 203–206. [Google Scholar] - Han, Y.; Byun, Y. Automatic and accurate registration of VHR optical and SAR images using a quadtree structure. Int. J. Remote Sens.
**2015**, 36, 2277–2295. [Google Scholar] [CrossRef] - Yang, A.; Li, Y.; Kong, F.; Wang, G.; Chen, E. Security control redundancy allocation technology and security keys based on Internet of Things. IEEE Access
**2018**, 6, 50187–50196. [Google Scholar] [CrossRef] - Mnak, G.; Altun, I.; Olgun, M. Fixed points of f-contractive type fuzzy mappings. J. Intell. Fuzzy Syst.
**2017**, 33, 1435–1439. [Google Scholar] [CrossRef] - Esteban, M.; Núñez, E.P.; Torres, F. Bifurcation analysis of hysteretic systems with saddle dynamics. Appl. Math. Nonlinear Sci.
**2017**, 2, 449–464. [Google Scholar] [CrossRef] - Simone, A.; Navara, M.; Pták, P. States on systems of sets that are closed under symmetric difference. Math. Nachr.
**2016**, 288, 1995–2000. [Google Scholar] [CrossRef]

**Figure 3.**Multi view data generation framework for symmetric difference kernel SAR images based on the GAN network model.

Number | Data Set | Data Generation Algorithm | Average Classification Accuracy/% | Overfitting Ratio |
---|---|---|---|---|

1 | Heavy fog weather situation map | None | 22.3 | 4.48 |

2 | Heavy fog weather situation map | Affine transformation algorithm | 75.4 | 1.33 |

3 | Heavy fog weather situation map | Algorithm in this paper | 89.1 | 1.08 |

4 | Clear weather situation map | None | 35.6 | 2.17 |

5 | Clear weather situation map | Affine transformation algorithm | 77.2 | 1.21 |

6 | Clear weather situation map | Algorithm in this paper | 93.8 | 0.94 |

7 | Thunderstorm weather situation map | None | 12.1 | 3.47 |

8 | Thunderstorm weather situation map | Affine transformation algorithm | 65.2 | 1.31 |

9 | Thunderstorm weather situation map | Algorithm in this paper | 79.5 | 1.25 |

**Table 2.**Results of quantitative comparison of the comparison algorithm and the algorithm in this paper.

$\mathbf{Percentage}\text{}{\mathit{B}}_{\mathit{i}}$$/\mathbf{Cumulative}\text{}\mathbf{Percentage}\text{}{\mathit{S}}_{\mathit{i}}$ | This Paper’s Algorithm | Canny Operator | ROA Detector |
---|---|---|---|

B_{0} | 96.85 | 40.00 | 38.79 |

S_{0} | 54.97 | 40.00 | 38.79 |

B_{1} | 44.29 | 24.91 | 42.10 |

S_{1} | 84.29 | 79.88 | 80.89 |

B_{2} | 10.06 | 5.83 | 7.14 |

S_{2} | 94.35 | 85.71 | 88.03 |

B_{3} | 2.73 | 4.69 | 5.03 |

S_{3} | 97.08 | 90.40 | 93.06 |

© 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Zhang, Z.; Liu, Y.; Liu, T.; Li, Y.; Ye, W.
Edge Detection Algorithm of a Symmetric Difference Kernel SAR Image Based on the GAN Network Model. *Symmetry* **2019**, *11*, 557.
https://doi.org/10.3390/sym11040557

**AMA Style**

Zhang Z, Liu Y, Liu T, Li Y, Ye W.
Edge Detection Algorithm of a Symmetric Difference Kernel SAR Image Based on the GAN Network Model. *Symmetry*. 2019; 11(4):557.
https://doi.org/10.3390/sym11040557

**Chicago/Turabian Style**

Zhang, Ziwen, Yijun Liu, Tie Liu, Yang Li, and Wujian Ye.
2019. "Edge Detection Algorithm of a Symmetric Difference Kernel SAR Image Based on the GAN Network Model" *Symmetry* 11, no. 4: 557.
https://doi.org/10.3390/sym11040557