Fast texture classification of denoised SAR image patches using GLCM on Spark

ersoy, okan; OĞUL, İskender Ülgen; Ozcan, Caner

doi:10.3906/elk-1904-7

Fast texture classification of denoised SAR image patches using GLCM on Spark

Caner ÖZCAN, (Karabük Üniversitesi)

Okan ERSOY, (Purdue University)

İskender Ülgen OĞUL (İzmir Yüksek Teknoloji Enstitüsü)

Turkish Journal of Electrical Engineering and Computer Sciences

3 0

Yıl: 2020 Cilt: 28 Sayı: 1 Sayfa Aralığı: 182 - 195 Metin Dili: İngilizce DOI: 10.3906/elk-1904-7 İndeks Tarihi: 30-04-2020

Fast texture classification of denoised SAR image patches using GLCM on Spark

Öz:

Classification of a synthetic aperture radar (SAR) image is an essential process for SAR image analysisand interpretation. Recent advances in imaging technologies have allowed data sizes to grow, and a large number ofapplications in many areas have been generated. However, analysis of high-resolution SAR images, such as classification,is a time-consuming process and high-speed algorithms are needed. In this study, classification of high-speed denoisedSAR image patches by using Apache Spark clustering framework is presented. Spark is preferred due to its powerfulopen-source cluster-computing framework with fast, easy-to-use, and in-memory analytics. Classification of SAR imagesis realized on patch level by using the supervised learning algorithms embedded in the Spark machine learning library.The feature vectors used as the classifier input are obtained using gray-level cooccurrence matrix which is chosen toquantitatively evaluate textural parameters and representations. SAR image patches used to construct the featurevectors are first applied to the noise reduction algorithm to obtain a more accurate classification accuracy. Experimentalstudies were carried out using naive Bayes, decision tree, and random forest algorithms to provide comparative results,and significant accuracies were achieved. The results were also compared with a state-of-the-art deep learning method.TerraSAR-X images of high-resolution real-world SAR images were used as data.

Anahtar Kelime:

Konular: Mühendislik, Elektrik ve Elektronik Bilgisayar Bilimleri, Yazılım Mühendisliği Bilgisayar Bilimleri, Sibernitik Bilgisayar Bilimleri, Bilgi Sistemleri Bilgisayar Bilimleri, Donanım ve Mimari Bilgisayar Bilimleri, Teori ve Metotlar Bilgisayar Bilimleri, Yapay Zeka

Belge Türü: Makale Makale Türü: Araştırma Makalesi Erişim Türü: Erişime Açık

[1] Moreira A, Prats-Iraola P, Younis M, Krieger G, Hajnsek I et al. A tutorial on synthetic aperture radar. IEEE Geoscience and Remote Sensing Magazine 2013; 1 (1): 6-43. doi: 10.1109/MGRS.2013.22483011
[2] Sakarya U, Demirpolat C. SAR image time-series analysis framework using morphological operators and global and local information-based linear discriminant analysis. Turkish Journal of Electrical Engineering & Computer Sciences 2018; 26: 2958-2966. doi:10.3906/elk-1712-339
[3] Chang YL, Chiang CY, Chen KS. SAR image simulation with application to target recognition. Progress in Electromagnetics Research 2011; 119: 35-57. doi: 10.2528/PIER11061507
[4] Horritt MS. A statistical active contour model for SAR image segmentation. Image and Vision Computing 1999; 17 (3-4): 213-224. doi: 10.1016/S0262-8856(98)00101-2
[5] Dekker RJ. Speckle filtering in satellite SAR change detection imagery. International Journal of Remote Sensing 1998; 19 (6): 1133-1146. doi: 10.1080/014311698215649
[6] Ampe EM, Vanhamel I, Salvadore E, Dams J, Bashir I et al. Impact of urban land-cover classification on groundwater recharge uncertainty. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2012; 5 (6): 1859-1867. doi: 0.1109/JSTARS.2012.2206573
[7] Attema EPW, Duchossois G, Kohlhammer G. Ers-1/2 SAR land applications: overview and main results. In: IEEE 1998 International Geoscience and Remote Sensing Symposium Proceedings; Seattle, WA, USA; 1998. pp. 1796-1798.
[8] Gamba P, Aldrighi M. SAR data classification of urban areas by means of segmentation techniques and ancillary optical data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2012; 5 (4): 1140-1148. doi: 10.1109/JSTARS.2012.2195774
[9] Nafornita C, Isar A, Matanie N, Caba C. Solution of a big data problem. Simulator for denoising of single look complex SAR images. In: International Symposium on Signals Circuits and Systems; Iasi, Romania; 2017. pp. 1-4.
[10] Alonso K, Datcu M. Image information mining: an accelerated bayesian algorithm for data fusion of SAR big data. In: Proceedings of 10th European Conference on Synthetic Aperture Radar; Berlin, Germany; 2014. pp. 604-607.
[11] Tonye E, Fotsing J, Bernard EZ, Tankam NT, Kanaa T et al. Contribution of variogram and feature vector of texture for the classification of big size SAR images. In: Seventh International Conference on Signal Image Technology & Internet-Based Systems; Dijon, France; 2011. pp. 382-389.
[12] Dumitru CO, Schwarz G, Cui S, Espinoza-Molina D, Datcu M. Semi-automated semantic annotation of big archives of high resolution SAR images. In: Proceedings of EUSAR 11th European Conference on Synthetic Aperture Radar; Hamburg, Germany; 2016; pp. 687-690.
[13] Zhu H, Guo Y, Niu M, Yang G, Jiao L. Distributed SAR image change detection based on spark. In: IEEE 2015 International Geoscience and Remote Sensing Symposium; Milan, Italy; 2015. pp. 4149-4152.
[14] Zhu H, Guo Y, Niu M, Qiu L, Jiao L et al. SAR image change detection based on Spark-FLICM algorithm. In: IEEE 2016 International Geoscience and Remote Sensing Symposium; Beijing, China; 2016. pp. 3354-3357.
[15] Zhu H, Kou J, Qiu L, Guo Y, Niu M et al. Distributed SAR image change detection with opencl-enabled spark. In: Proceedings of the first Workshop on Emerging Technologies for software-defined and reconfigurable hardwareaccelerated Cloud Datacenters; New York, NY, USA; 2017. pp. 1-6.
[16] Sharma T, Shokeen V, Mathur S. Multiple K Means++ clustering of satellite image using Hadoop MapReduce and Spark. International Journal of Advanced Studies in Computer Science and Engineering 2016; 5 (4): 23-31.
[17] Huang W, Meng L, Zhang D, Zhang W. In-memory parallel processing of massive remotely sensed data using an Apache Spark on Hadoop YARN model. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2017; 10 (1): 3-19. doi: 10.1109/JSTARS.2016.2547020
[18] Yu Y, Acton ST. Speckle reducing anisotropic diffusion. IEEE Transactions on Image Processing 2002; 11 (11): 1260-1270. doi: 10.1109/TIP.2002.804276
[19] Argenti F, Bianchi T, Lapini A, Alparone L. Fast MAP despeckling based on laplacian-gaussian modeling of wavelet coefficients. IEEE Geoscience and Remote Sensing Letters 2012; 9 (1): 13-17. doi: 10.1109/LGRS.2011.2158798
[20] Ozcan C, Sen B, Nar F. Sparsity-driven despeckling for SAR images. IEEE Geoscience Remote Sensing Letters 2016; 3 (1): 115-119. doi: 10.1109/LGRS.2015.2499445
[21] Haralick RM, Shanmugam K, Dinstein IH. Textural features for image classification. IEEE Transactions on Systems, Man, and Cybernetics 1973; SMC-3 (6): 610-621. doi: 10.1109/TSMC.1973.4309314
[22] Soh L, Tsatsoulis C. Texture analysis of SAR sea ice imagery using gray level co-occurances matrices. IEEE Transactions on Geoscience and Remote Sensing 1999; 37 (2): 780-795. doi: 10.1109/36.752194
[23] Lv W, Yu Q, Yu W. Water extraction in SAR images using GLCM and Support Vector Machine. In IEEE 10th International Conference on Signal Processing Proceedings; Beijing, China; 2010. pp. 740-743.
[24] Zhao J, Guo W, Cui S, Zhang Z, Yu W. Convolutional Neural Network for SAR image classification at patch level. In IEEE International Geoscience and Remote Sensing Symposium; Beijing, China; 2016; pp. 945-948.
[25] Ozcan C, Ersoy O, Ogul IU. Classification of SAR image patches with Apache Spark using GLCM texture features. In: International Conference on Advanced Technologies 3rd World Conference on Big Data; Izmir, Turkey; 2018. pp. 1-7.
[26] Karau H, Konwinski A, Wendell P, Zaharia M. Learning Spark: Lightning-Fast Big Data Analytics. 1st ed. Sebastopol, CA, USA: O’Reilly Media, Inc., 2015.
[27] Han J, Kamber M, Pei J. Data Mining: Concepts and Techniques. Waltham, MA, USA: Elsevier, Second Edition, 2006.
[28] Rojas I, Joya G, Catala A. Advances in Computational Intelligence. Cadiz, Spain: Springer, 2017.
[29] Karau H, Warren R. High Performance Spark: Best Practices for Scaling and Optimizing Apache Spark. Sebastopol, CA, USA: O’Reilly Media, Inc., First Edition, 2017.
[30] Karim R, Alla S. Scala and Spark for Big Data Analytics: Explore The Concepts of Functional Programming, Data Streaming, and Machine Learning. Birmingham, UK: Packt Publishing; First Edition, 2017.
[31] Man W, Ji Y, Zhang Z. Image classification based on improved random forest algorithm. In: IEEE 3rd International Conference on Cloud Computing and Big Data Analysis; Chengdu, China; 2018. pp. 346-350.
[32] LeCun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proceedings of the IEEE 1998; 86 (11): 2278-2324. doi: 10.1109/5.726791

APA	Ozcan C, ersoy o, OĞUL İ (2020). Fast texture classification of denoised SAR image patches using GLCM on Spark. , 182 - 195. 10.3906/elk-1904-7
Chicago	Ozcan Caner,ersoy okan,OĞUL İskender Ülgen Fast texture classification of denoised SAR image patches using GLCM on Spark. (2020): 182 - 195. 10.3906/elk-1904-7
MLA	Ozcan Caner,ersoy okan,OĞUL İskender Ülgen Fast texture classification of denoised SAR image patches using GLCM on Spark. , 2020, ss.182 - 195. 10.3906/elk-1904-7
AMA	Ozcan C,ersoy o,OĞUL İ Fast texture classification of denoised SAR image patches using GLCM on Spark. . 2020; 182 - 195. 10.3906/elk-1904-7
Vancouver	Ozcan C,ersoy o,OĞUL İ Fast texture classification of denoised SAR image patches using GLCM on Spark. . 2020; 182 - 195. 10.3906/elk-1904-7
IEEE	Ozcan C,ersoy o,OĞUL İ "Fast texture classification of denoised SAR image patches using GLCM on Spark." , ss.182 - 195, 2020. 10.3906/elk-1904-7
ISNAD	Ozcan, Caner vd. "Fast texture classification of denoised SAR image patches using GLCM on Spark". (2020), 182-195. https://doi.org/10.3906/elk-1904-7

APA	Ozcan C, ersoy o, OĞUL İ (2020). Fast texture classification of denoised SAR image patches using GLCM on Spark. Turkish Journal of Electrical Engineering and Computer Sciences, 28(1), 182 - 195. 10.3906/elk-1904-7
Chicago	Ozcan Caner,ersoy okan,OĞUL İskender Ülgen Fast texture classification of denoised SAR image patches using GLCM on Spark. Turkish Journal of Electrical Engineering and Computer Sciences 28, no.1 (2020): 182 - 195. 10.3906/elk-1904-7
MLA	Ozcan Caner,ersoy okan,OĞUL İskender Ülgen Fast texture classification of denoised SAR image patches using GLCM on Spark. Turkish Journal of Electrical Engineering and Computer Sciences, vol.28, no.1, 2020, ss.182 - 195. 10.3906/elk-1904-7
AMA	Ozcan C,ersoy o,OĞUL İ Fast texture classification of denoised SAR image patches using GLCM on Spark. Turkish Journal of Electrical Engineering and Computer Sciences. 2020; 28(1): 182 - 195. 10.3906/elk-1904-7
Vancouver	Ozcan C,ersoy o,OĞUL İ Fast texture classification of denoised SAR image patches using GLCM on Spark. Turkish Journal of Electrical Engineering and Computer Sciences. 2020; 28(1): 182 - 195. 10.3906/elk-1904-7
IEEE	Ozcan C,ersoy o,OĞUL İ "Fast texture classification of denoised SAR image patches using GLCM on Spark." Turkish Journal of Electrical Engineering and Computer Sciences, 28, ss.182 - 195, 2020. 10.3906/elk-1904-7
ISNAD	Ozcan, Caner vd. "Fast texture classification of denoised SAR image patches using GLCM on Spark". Turkish Journal of Electrical Engineering and Computer Sciences 28/1 (2020), 182-195. https://doi.org/10.3906/elk-1904-7