• P-ISSN 0974-6846 E-ISSN 0974-5645

Indian Journal of Science and Technology


Indian Journal of Science and Technology

Year: 2022, Volume: 15, Issue: 9, Pages: 371-385

Original Article

Deep Learning Approach with Optimization Algorithm for Reducing the Training and Testing Time in SAR Image Detection and Recognition

Received Date:12 August 2021, Accepted Date:21 January 2022, Published Date:05 March 2022


Objective: - To reduce training and testing time in SAR image detection and recognition using optimization algorithm. Methods: SAR images have achieved a prominent position in the arena of remote sensing and satellite technology. SAR image processing has many applications in different areas like agriculture, mineral exploration, resource management and environmental monitoring. To carry out this research works, MSTAR dataset was were used with six classes. The collected dataset was preprocessed with filtering algorithms to remove the speckle noise from the image. Then, image segmentation which is essential expertise for image processing has been done with aim of rationalizing and changing image representation into more meaningful and easier to analyze. The characters of Hue, Intensity, Saturation (H, I, S) were applied to acquire the information of the pixels of the target image. By doing so, color information and edge extraction were done, since it was the basic idea to achieve the segmented image from its background. Next, feature extraction has been done using DNNs through three stages (Low, middle and high level feature extraction). At low level feature extraction, the image edge and lines were extracted while image front or noses were extracted at middle level feature extraction. Then, all image features were combined at the high level feature extraction and thus all features were combined to form high-level features, because they were primitive images features. After doing all the above, detection has been done to locate the presence of objects in an image using bounding box regression model. Finally, for the SAR image recognition, the pre-trained CNN models such as ResNet-50, AlexNet, and VGG16 were used to compare their performance with the proposed model. In SAR image detection and recognition, the high training and testing time is founded as a challenging. Thus, to reduce such long training and testing time of SAR image detection and recognition, optimization algorithms such as Stochastic Gradient Descent with Momentum (SGDM), RMSProp and Adam optimization methods were used with the pre-training and proposed CNN model. Findings: Preprocessing was carried out using Median, Guided Filter (GF), Lee, Box, Adaptive or Wiener filter algorithms were used and their performances were also compared in PSNR, SNR and MSE values and from those all used algorithms, the GF achieves better performance in high PSNR value of 37.8342. The performance of the all three pre-trained models and the proposed models were compared in accuracy and speed. The AlexNet, ResNet-50, VGG16 and proposed models achieved accuracy of 89%, 92%, 86% and 95% respectively and proposed model achieved the best performance. Among the used four models with Optimization methods, the Proposed Model with SGDM took very least time for Training (26’ and 49s) and for Testing (17s). Novelty: New Deep Network Model was successfully designed, developed and used along with Optimization algorithms for reducing the training and testing time in SAR image detection and recognition.

Keywords: ResNet50; VGG16; SAR image; Optimization algorithms


  1. Sun S, Cao Z, Zhu H, Zhao J. A Survey of Optimization Methods From a Machine Learning Perspective. IEEE Transactions on Cybernetics. 2020;50(8):3668–3681. Available from: https://dx.doi.org/10.1109/tcyb.2019.2950779
  2. Cui Z, Dang S, Cao Z, Wang S, Liu N. SAR Target Recognition in Large Scene Images via Region-Based Convolutional Neural Networks. Remote Sensing. 2018;10(5):776. doi: 1
  3. Sutskever I, Martens J, Dahl G, Hinton G. On the importance of initialization and momentum in deep learning. International Conference on Machine Learning. 2013;p. 1139–1147. Available from: http://proceedings.mlr.press/v28/sutskever13.html
  4. Duchi J, Hazan E, Singer Y. Adaptive sub gradient methods for online learning and stochastic optimization. Journal of Machine Learning Research. 2011;12:2121–2159. Available from: https://escholarship.org/uc/item/4ck5k544
  5. Parks F. A study of the Exponentiated Gradient +/- algorithm for stochastic optimization of neural networks. Powered by the California Digital Library University of California. 2019. Available from: https://escholarship.org/uc/item/4ck5k544
  6. Chatfield K, Simonyan K, Vedaldi A, Zisserman A. Return of the Devil in the Details: Delving Deep into Convolutional Nets. Proceedings of the British Machine Vision Conference 2014. 2014. doi: 10.5244/c.28.6
  7. Zhang K, Zuo W, Chen Y, Meng D, Zhang L. Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising. IEEE Transactions on Image Processing. 2017;26(7):3142–3155. Available from: https://dx.doi.org/10.1109/tip.2017.2662206
  8. Girshick R, Donahue J, Darrell T, Malik J. Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. 2014 IEEE Conference on Computer Vision and Pattern Recognition. 2014;1:5000. doi: 10.1109/CVPR.2014.81
  9. Kang M, Ji K, Leng X, Xing X, Zou H. Synthetic Aperture Radar Target Recognition with Feature Fusion Based on a Stacked Autoencoder. Sensors. 2017;17(12):192. Available from: https://dx.doi.org/10.3390/s17010192
  10. Felzenszwalb PF, Girshick RB, McAllester D, Ramanan D. Object Detection with Discriminatively Trained Part-Based Models. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2010;32(9):1627–1645. Available from: https://dx.doi.org/10.1109/tpami.2009.167
  11. Bentes C, Velotto D, Tings B. Ship Classification in TerraSAR-X Images With Convolutional Neural Networks. IEEE Journal of Oceanic Engineering. 2018;43(1):258–266. Available from: https://dx.doi.org/10.1109/joe.2017.2767106
  12. Li R, Liu W, Yang L, Sun S, Hu W, Zhang F, et al. DeepUNet: A Deep Fully Convolutional Network for Pixel-Level Sea-Land Segmentation. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2018;11(11):3954–3962. Available from: https://dx.doi.org/10.1109/jstars.2018.2833382
  13. Ali W, Wegner AE, Gaunt RE, Deane CM, Reinert G. Comparison of large networks with sub-sampling strategies. Scientific Reports. 2016;6(1):24–29. Available from: https://dx.doi.org/10.1038/srep28955
  14. Aghababaee H, Amini J, Tzeng YC. Improving change detection methods of SAR images using fractals. Scientia Iranica. 2013;20(1):15–22. Available from: https://dx.doi.org/10.1016/j.scient.2012.11.006
  15. Zhao ZQ, Zheng P, Xu ST, Wu X. Object Detection With Deep Learning: A Review. IEEE Transactions on Neural Networks and Learning Systems. 2019;30(11):3212–3232. Available from: https://dx.doi.org/10.1109/tnnls.2018.2876865
  16. Nedjah N, Mourelle LDM. Fast Pre-Processing for the Sliding Window Method Using Genetic Algorithms. International journal of computers, Systems, Signals. 2003;4(2):11–21. Available from: http://citeseerx.ist.psu.edu/viewdoc/citations?doi=
  17. Chen S, Wang H, Xu F, Jin YQ. Target Classification Using the Deep Convolutional Networks for SAR Images. IEEE Transactions on Geoscience and Remote Sensing. 2016;54(8):4806–4817. Available from: https://dx.doi.org/10.1109/tgrs.2016.2551720
  18. Kang M, Ji K, Leng X, Xing X, Zou H. Synthetic Aperture Radar Target Recognition with Feature Fusion Based on a Stacked Autoencoder. Sensors. 2017;17(12):192. Available from: https://dx.doi.org/10.3390/s17010192
  19. Nagesa Y, Nagarajan S, Negesa F. Performance Comparison of SAR Image Speckle Noise Removal Algorithms. International Journal of Computer Applications. 2021;183(18):14–19. Available from: https://dx.doi.org/10.5120/ijca2021921525
  20. Sun Y, Wang X, Tang X. Deep Learning Face Representation from Predicting 10,000 Classes. 2014 IEEE Conference on Computer Vision and Pattern Recognition. 2014;p. 1891–1898. doi: 10.1109/CVPR.2014.244
  21. Wang Y, Han P, Lu X, Wu R, Huang J. The Performance Comparison of Adaboost and SVM Applied to SAR ATR. 2006 CIE International Conference on Radar. 2006. doi: 10.1109/ICR.2006.343515
  22. Khan A, Sohail A, Zahoora U, Qureshi AS. A survey of the recent architectures of deep convolutional neural networks. Artificial Intelligence Review. 2020;53(8):5455–5516. Available from: https://dx.doi.org/10.1007/s10462-020-09825-6
  23. Chuang KS, Tzeng HL, Chen S, Wu J, Chen TJ. Fuzzy c-means clustering with spatial information for image segmentation. Computerized Medical Imaging and Graphics. 2006;30(1):9–15. Available from: https://dx.doi.org/10.1016/j.compmedimag.2005.10.001
  24. Donahue J. DeCAF: A deep convolutional activation feature for generic visual recognition. 31st International Conference of Machine Learning. 2014;2:988–996. Available from: http://proceedings.mlr.press/v32/donahue14.html
  25. Pang S, Meng F, Wang X, Wang J, Song T, Wang X, et al. VGG16-T: A Novel Deep Convolutional Neural Network with Boosting to Identify Pathological Type of Lung Cancer in Early Stage by CT Images. International Journal of Computational Intelligence Systems. 2020;13(1):771. Available from: https://dx.doi.org/10.2991/ijcis.d.200608.001


© 2022 Selvam et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

Published By Indian Society for Education and Environment (iSee)


Subscribe now for latest articles and news.