Kaynaştırılmış Görüntülerden Elde Edilen Gabor Doku Özellikleri ile DVM Sınıflandırma Performansının İyileştirilmesi

Yıl 2020, Cilt: 1 Sayı: 1, 34 - 44, 31.03.2020

Çiğdem Şerifoğlu Yılmaz , Oguz Güngör

Öz

Görüntü kaynaştırma, uzaktan algılanan verilerin yorumlanabilirliğini ve işlevselliğini artırmak için en yaygın olarak kullanılan tekniklerden biridir. Bu çalışmanın amacı Destek Vektör Makineleri (DVM) sınıflandırma algoritmasının performansının kaynaştırılmış görüntülerden elde edilen doku özellikleri yardımıyla iyileştirilmesidir. Bu amaçla, ilk aşama olarak bir WorldView-2 çok bantlı görüntüsü bir WorldView-2 pankromatik görüntüsü ile PCA (Principal Component Analysis), WSB (Wavelet Single Band), GS (Gram-Schmidt), BRV (Brovey), EHL (Ehlers), HCS (Hyperspherical Colour Space), HPF (High-Pass Filtering) ve MCV (Multiplicative) yöntemleri kullanılarak kaynaştırılmıştır. Daha sonra her bir kaynaştırılmış görüntüye Temel Bileşenler Analizi uygulanmıştır. Her bir kaynaştırılmış görüntü için elde edilen birinci temel bileşen Gabor doku özelliklerinin çıkartılması amacıyla kullanılmıştır. Son aşama olarak da elde edilen doku özellikleri girdi çok bantlı görüntüye eklenmiştir. Elde edilen bu görüntüler DVM algoritmasıyla sınıflandırılarak kullanılan metodolojinin sınıflandırma doğruluğunu ne derece etkilediği incelenmiştir. Sonuç olarak, GS yöntemiyle elde edilen Gabor doku özelliklerinin %19.3 artış ile sınıflandırma doğruluğunu en fazla oranda arttıran doku özelliği olduğu ve PCA yöntemiyle elde edilen Gabor doku özelliklerinin ise %18.7 artış ile sınıflandırma doğruluğunu en fazla oranda arttıran ikinci doku özelliği olduğu tespit edilmiştir.

Anahtar Kelimeler

Doku özellik çıkarımı, Görüntü kaynaştırma, Gabor doku özellikleri, Temel bileşenler analizi, Görüntü sınıflandırma

Improving SVM Classification Accuracy with Image Fusion-Based Gabor Texture Features

Öz

Image fusion is one of the most common techniques used to enhance the interpretability and functionality of remotely sensed data. The aim of this study was to improve the performance of the SVM (Support Vector Machines) classifier with the aid of texture features (TF) extracted from fused images. As a first step, the spatial resolution of the WorldView-2 MS (multispectral) imagery was increased by fusing it with a WorldView-2 PAN (panchromatic) image using the PCA (Principal Component Analysis), WSB (Wavelet Single Band), GS (Gram-Schmidt), BRV (Brovey), EHL (Ehlers), HCS (Hyperspherical Colour Space), HPF (High-Pass Filtering) and MCV (Multiplicative) algorithms. A PCA transform was then applied on all fused images. The first principal component obtained from each fused image was used to extract the Gabor TFs. As a final step, extracted Gabor TFs were combined with the original MS image. Resultant images were classified with the SVM algorithm to investigate to what degree the used methodology affect the classification accuracy. The results showed that the GS fusion-based Gabor TFs provided the greatest classification accuracy increase with 19.3%, whereas the PCA fusion-based Gabor TFs resulted in the second best classification accuracy increase with 18.7%.

Anahtar Kelimeler

Texture feature extraction, Image fusion, Gabor texture features, Principal component analysis, Image classification

Kaynakça

• Acerbi-Junior, F. W., Clevers, J. G. P. W., & Schaepman, M. E. (2006). The assessment of multi-sensor image fusion using wavelet transforms for mapping the Brazilian Savanna. International Journal of Applied Earth Observation and Geoinformation, 8(4), 278-288. doi:10.1016/j.jag.2006.01.001.
• Akar, Ö. & Güngör, O. (2015). Integrating multiple texture methods and NDVI to the Random Forest classification algorithm to detect tea and hazelnut plantation areas in northeast Turkey. International Journal of Remote Sensing, 36(2), 442-464. doi:10.1080/01431161.2014.995276.
• Almendros-Jiménez, J. M., Domene, L., & Piedra-Fernandez, J. A. (2012). A framework for ocean satellite image classification based on ontologies. IEEE Journal of selected topics in applied earth observations and remote sensing, 6(2), 1048-1063. doi:10.1109/JSTARS.2012.2217479.
• Angelo, N. P., & Haertel, V. (2003). On the application of Gabor filtering in supervised image classification. International Journal of Remote Sensing, 24(10), 2167-2189. doi:10.1080/01431160210163146.
• Augusteijn, M. F., Clemens, L. E., & Shaw, K. A. (1995). Performance evaluation of texture measures for ground cover identification in satellite images by means of a neural network classifier. IEEE Transactions on Geoscience and Remote Sensing, 33(3), 616-626. doi:10.1109/36.387577.
• Baraldi, A., & Panniggiani, F. (1995). An investigation of the textural characteristics associated with gray level cooccurrence matrix statistical parameters. IEEE Transactions on Geoscience and Remote Sensing, 33(2), 293-304. doi:10.1109/TGRS.1995.8746010.
• Bigdeli, M., Vakilian, M., & Rahimpour, E. (2012). Transformer winding faults classification based on transfer function analysis by support vector machine. IET Electric Power Applications, 6(5), 268-276. doi:10.1049/iet-epa.2011.0232.
• Butusov, O. B. (2003). Textural classification of forest types from Landsat 7 imagery. Mapping Sciences and Remote Sensing, 40(2), 91-104. doi:10.2747/0749-3878.40.2.91.
• Chavez, A., & Kwarteng, P. (1989). Extracting spectral contrast in Landsat Thematic Mapper image data using selective principal component analysis. Photogrammetric Engineering and Remote Sensing, 55, 339-348.
• Chen, K. S., Yen, S. K., & Tsay, D. W. (1997). Neural classification of SPOT imagery through integration of intensity and fractal information. International Journal of Remote Sensing, 18(4), 763-783. doi:10.1080/014311697218746.
• Congalton, R. G., & Green, K. (1999). Assessing the Accuracy of Remotely Sensed Data: Principles and Practices. Boca Raton, FL: Lewis.
• Crippen, R. E. (1989). A simple spatial filtering routine for the cosmetic removal of scan-line noise from Landsat TM P-tape imagery. Photogrammetric Engineering & Remote Sensing, 55, 327–331.
• Damodaran, B. B., & Nidamanuri, R. R. (2014). Dynamic linear classifier system for hyperspectral image classification for land cover mapping. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7(6), 2080-2093. doi:10.1109/JSTARS.2013.2294857.
• Devi, T. A. M., & Rekha, N. (2013). Hyperspectral Image Classification Using Spatial and Spectral Features. International Journal of Scientific & Engineering Research, 4(7), 1843-1847.
• Du, Y., Vachon, P. W., & Van der Sanden, J. J. (2003). Satellite image fusion with multiscale wavelet analysis for marine applications: preserving spatial information and minimizing artifacts (PSIMA). Canadian Journal of Remote Sensing, 29(1), 14-23. doi:10.5589/m02-079.
• Dube, T., Gumindoga, W., & Chawira, M. (2014). Detection of land cover changes around Lake Mutirikwi, Zimbabwe, based on traditional remote sensing image classification techniques. African Journal of Aquatic Science, 39(1), 89-95. doi:10.2989/16085914.2013.870068.
• Eddy, P., Smith, A., Hill, B., Peddle, D., Coburn, C., & Blackshaw, R. (2006, July). Comparison of neural network and maximum likelihood high resolution image classification for weed detection in crops: Applications in precision agriculture. In 2006 IEEE International Symposium on Geoscience and Remote Sensing (pp. 116-119). IEEE. doi:10.1109/IGARSS.2006.35.
• Ehlers, M. (2004, October). Spectral characteristics preserving image fusion based on Fourier domain filtering. In Remote sensing for environmental monitoring, GIS applications, and geology IV (Vol. 5574, pp. 1-13). International Society for Optics and Photonics. doi: 10.1117/12.565160.
• ERDAS IMAGINE Field Guide 2013, Leica Geosystems, Atlanta, GA: ERDAS.
• Gitas, I. Z., Mitri, G. H., & Ventura, G. (2004). Object-based image classification for burned area mapping of Creus Cape, Spain, using NOAA-AVHRR imagery. Remote Sensing of Environment, 92(3), 409-413. doi: 10.1016/j.rse.2004.06.006.
• Gogineni, R., & Chaturvedi, A. (2018). Sparsity inspired pan-sharpening technique using multi-scale learned dictionary. ISPRS journal of photogrammetry and remote sensing, 146, 360-372.doi:10.1016/j.isprsjprs.2018.10.009.
• Hallada, W. A., & Cox, S. (1983, May). Image sharpening for mixed spatial and spectral resolution satellite systems. Proceedings of the 17th International Symposium on Remote Sensing of Environment, pp. 1023-1032, Ann Arbor, MI, USA.
• Haralick, R. M., Shanmugam, K., & Dinstein, I. H. (1973). Textural features for image classification. IEEE Transactions on systems, man, and cybernetics, (6), 610-621. doi: 10.1109/TSMC.1973.4309314.
• Hermosilla, T., Almonacid, J., Fernández-Sarría, A., Ruiz, L. A., & Recio, J. A. (2010). Combining features extracted from imagery and lidar data for object-oriented classification of forest areas. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 38, 194-200.
• Hill, P. R., Canagarajah, C. N., & Bull, D. R. (2002, September). Image Fusion Using Complex Wavelets. In BMVC (pp. 1-10).
• Huang, C., Davis, L. S., & Townshend, J. R. G. (2002). An assessment of support vector machines for land cover classification. International Journal of Remote Sensing, 23(4), 725-749. doi: 10.1080/01431160110040323.
• Huang, Z. C., Chan, P. P., Ng, W. W., & Yeung, D. S. (2010, July). Content-based image retrieval using color moment and Gabor texture feature. In 2010 International Conference on Machine Learning and Cybernetics (Vol. 2, pp. 719-724). IEEE, Qingdao, China. doi: 10.1109/ICMLC.2010.5580566.
• Jin, H., Li, P., Cheng, T., & Song, B. (2012). Land cover classification using CHRIS/PROBA images and multi-temporal texture. International Journal of Remote Sensing, 33(1), 101-119. doi: 10.1080/01431161.2011.584077.
• Johnson, B. A., Tateishi, R., & Hoan, N. T. (2013). A hybrid pansharpening approach and multiscale object-based image analysis for mapping diseased pine and oak trees. International Journal of Remote Sensing, 34(20), 6969-6982. doi:10.1080/01431161.2013.810825.
• Johnsson, K. (1994). Segment-based land-use classification from SPOT satellite data. Photogrammetric Engineering and Remote Sensing, 60(1), 47-54.
• Kedzierski, M., Wilinska, M., Wierzbicki, D., Fryskowska, A., & Delis, P. (2014, May). Image data fusion for flood plain mapping. In Proceedings of the 9th International Conference on Environmental Engineering, Vilnius, Lithuania (pp. 22-23).
• Klonus, S., & Ehlers, M. (2007). Image fusion using the Ehlers spectral characteristics preservation algorithm. GIScience & Remote Sensing, 44(2), 93-116. doi: 10.2747/1548-1603.44.2.93.
• Kollár, S., Vekerdy, Z., & Márkus, B. (2013). Aerial image classification for the mapping of riparian vegetation habitats. Acta Silvatica et Lignaria Hungarica, 9(1), 119-133.
• Kurosu, T., Yokoyama, S., Fujita, M., & Chiba, K. (2001). Land use classification with textural analysis and the aggregation technique using multi-temporal JERS-1 L-band SAR images. International Journal of Remote Sensing, 22(4), 595-613. doi: 10.1080/01431160050505874.
• Laben, C. A., & Brower, B. V. (2000). Process for enhancing the spatial resolution of multispectral imagery using pan-sharpening. US Patent No. 6,011,875, filed 29 April 1998 and issued 4 January 2000 to the Eastman Kodak Company.
• Lauer, M., & Aswani, S. (2008). Integrating indigenous ecological knowledge and multi-spectral image classification for marine habitat mapping in Oceania. Ocean & Coastal Management, 51(6), 495-504. doi: 10.1016/j.ocecoaman.2008.04.006.
• Lloyd, C. D., Berberoglu, S., Curran, P. J., & Atkinson, P. M. (2004). A comparison of texture measures for the per-field classification of Mediterranean land cover. International Journal of Remote Sensing, 25(19), 3943-3965. doi: 10.1080/0143116042000192321.
• Low, H. K., Chuah, H. T., & Ewe, H. T. (1999). A Neural Network Landuse Classifier for SAR Images using Textural and Fractal Information. Geocarto International, 14(1), 66-73. doi: 10.1080/10106049908542096.
• Mathew, A. R., & Anto, P. B. (2017). Tumor detection and classification of MRI brain image using wavelet transform and SVM. In IEEE 2017 International Conference on Signal Processing and Communication (ICSPC), pp. 75-78, Coimbatore, India. doi: 10.1109/CSPC.2017.8305810.
• Mathur, A., & Foody, G. M. (2008). Multiclass and binary SVM classification: Implications for training and classification users. IEEE Geoscience and Remote Sensing Letters, 5(2), 241-245. doi: 10.1109/LGRS.2008.915597.
• Melgani, F., & Bruzzone, L. (2004). Classification of hyperspectral remote sensing images with support vector machines. IEEE Transactions on Geoscience and Remote Sensing, 42(8), 1778-1790. doi: 10.1109/TGRS.2004.831865.
• Milgram, J., Cheriet, M., & Sabourin, R. (2006). “One against one” or “one against all”: Which one is better for handwriting recognition with SVMs? 10th International Workshop on Frontiers in Handwriting Recognition, Université de Rennes 1, La Baule, France.
• Nanni, L., Brahnam, S., Ghidoni, S., Menegatti, E., & Barrier, T. (2013). A comparison of methods for extracting information from the co-occurrence matrix for subcellular classification. Expert Systems with Applications, 40(18), 7457-7467. doi:10.1016/j.eswa.2013.07.047.
• Nyoungui, A. N., Tonye, E., & Akono, A. (2002). Evaluation of speckle filtering and texture analysis methods for land cover classification from SAR images. International Journal of Remote Sensing, 23(9), 1895-1925. doi:10.1080/01431160110036157.
• Omkar, S. N., Kumar, M. M., Mudigere, D., & Muley, D. (2007). Urban satellite image classification using biologically inspired techniques. In IEEE International Symposium on Industrial Electronics (pp. 1767-1772). doi:10.1109/ISIE.2007.4374873.
• Özdarıcı Ok, A., Akyürek, Z. (2013). Çok Tarihli Görüntü Sınıflandırmada Destek Vektör Makinaları ve Bulanık Mantık Yöntemi Kullanan Bölüt Tabanlı Bir Yaklaşım, Türkiye Ulusal Fotogrametri ve Uzaktan Algılama Birliği VII. Teknik Sempozyumu (TUFUAB’2013), pp. 1-6, Trabzon, Türkiye.
• Padwick, C., Deskevich, M., Pacifici, F., & Smallwood, S. (2010, April). WorldView-2 pan-sharpening. In Proceedings of the ASPRS 2010 Annual Conference, San Diego, CA, USA, (Vol. 2630, pp. 1-14).
• Pathak, V., & Dikshit, O. (2010). A new approach for finding an appropriate combination of texture parameters for classification. Geocarto International, 25(4), 295-313. doi: 10.1080/10106040903576195.
• Peli, T., Peli, E., Ellis, K. K., & Stahl, R. (1999, March). Multispectral image fusion for visual display. In Sensor Fusion: Architectures, Algorithms, and Applications III (Vol. 3719, pp. 359-368). International Society for Optics and Photonics.
• Petkov, N., & Wieling, M. (2008). Gabor filter for image processing and computer vision. On line, http://matlabserver.cs.rug.nl/edgedetectionweb/index.html. Accessed on 18 February 2020.
• Podest, E., & Saatchi, S. (2002). Application of multiscale texture in classifying JERS-1 radar data over tropical vegetation. International Journal of Remote Sensing, 23(7), 1487-1506. doi: 10.1080/01431160110093000.
• Pohl, C. (1996). Geometric aspects of multisensor image fusion for topographic map updating in the humid tropics, PhD thesis, University of Twente.
• Poulain, V., Inglada, J., Spigai, M., Tourneret, J. Y., & Marthon, P. (2011). High-Resolution Optical and SAR Image Fusion for Building Database Updating. IEEE Transactions on Geoscience and Remote Sensing, 49(8), 2900-2910. doi:10.1109/TGRS.2011.2113351.
• Ran, Q., Li, W., Du, Q., & Yang, C. (2015). Hyperspectral image classification for mapping agricultural tillage practices. Journal of Applied Remote Sensing, 9(1), 097298. doi:10.1117/1.JRS.9.097298.
• Rao, P. N., Sai, M. S., Sreenivas, K., Rao, M. K., Rao, B. R. M., Dwivedi, R. S., & Venkataratnam, L. (2002). Textural analysis of IRS-1D panchromatic data for land cover classification. International Journal of Remote Sensing, 23(17), 3327-3345. doi:10.1080/01431160110104665.
• Ricchetti, E. (2000). Multispectral satellite image and ancillary data integration for geological classification. Photogrammetric Engineering and Remote Sensing, 66(4), 429-435.
• Sambodo, K. A., Murni, A., & Kartasasmita, M. (2010). Classification of polarimetric-SAR data with neural network using combined features extracted from scattering models and texture analysis. International Journal of Remote Sensing and Earth Sciences, 4(1), 1-17. doi:10.30536/j.ijreses.2007.v4.a1212.
• Schowengerdt, R. A. (1980). Reconstruction of multispatial, multispectral image data using spatial frequency content. Photogrammetric Engineering and Remote Sensing, 46(10), 1325-1334.
• Serifoglu Yilmaz, C., Yilmaz, V., Gungor, O., & Shan, J. (2019). Metaheuristic pansharpening based on symbiotic organisms search optimization. ISPRS Journal of Photogrammetry and Remote Sensing, 158, 167-187. doi:10.1016/j.isprsjprs.2019.10.014.
• Shaker, A., Yan, W. Y., & El-Ashmawy, N. (2012). Panchromatic satellite image classification for flood hazard assessment. Journal of Applied Research and Technology, 10(6), 902-911.
• Tsagaris, V., & Anastassopoulos, V. (2005). Multispectral image fusion for improved RGB representation based on perceptual attributes. International Journal of Remote Sensing, 26(15), 3241-3254. doi:10.1080/01431160500127609.
• Vapnik, V. (1995). The Nature of Statistical Learning Theory. New York, Springer-Verlag.
• Vapnik, V. (1998). Statistical Learning Theory. New York, Springer-John Wiley.
• Yang, B., Kim, M., & Madden, M. (2012). Assessing optimal image fusion methods for very high spatial resolution satellite images to support coastal monitoring. GIScience & Remote Sensing, 49(5), 687-710. doi:10.2747/1548-1603.49.5.687.
• Yang, C., Everitt, J. H., & Murden, D. (2011). Evaluating high resolution SPOT 5 satellite imagery for crop identification. Computers and Electronics in Agriculture, 75(2), 347-354. doi:10.1016/j.compag.2010.12.012.
• Yang, J., Liu, L., Jiang, T., & Fan, Y. (2003). A modified Gabor filter design method for fingerprint image enhancement. Pattern Recognition Letters, 24(12), 1805-1817. doi:10.1016/S0167-8655(03)00005-9.
• Yang, M. D., Huang, K. S., Kuo, Y. H., Tsai, H., & Lin, L. M. (2017). Spatial and spectral hybrid image classification for rice lodging assessment through UAV imagery. Remote Sensing, 9(6), 583. doi:10.3390/rs9060583.
• Yılmaz, V. (2019). Kaynaştırılmış Görüntülerden Elde Edilen Doku Özellikleri ile DVM Sınıflandırma Performansının İyileştirilmesi. Geomatik, 4(3), 190-200. doi: 10.29128/geomatik.507613.
• Yilmaz, V., & Gungor, O. (2016). Determining the optimum image fusion method for better interpretation of the surface of the Earth. Norsk Geografisk Tidsskrift-Norwegian Journal of Geography, 70(2), 69-81. doi:10.1080/00291951.2015.1126761.
• Yilmaz, V., Konakoglu, B., Serifoglu, C., Gungor, O., & Gökalp, E. (2018). Image classification-based ground filtering of point clouds extracted from UAV-based aerial photos. Geocarto international, 33(3), 310-320. doi:10.1080/10106049.2016.1250825.
• Yilmaz, V., Serifoglu Yilmaz, C., Güngör, O., & Shan, J. (2020). A genetic algorithm solution to the gram-schmidt image fusion. International Journal of Remote Sensing, 41(4), 1458-1485. doi:10.1080/01431161.2019.1667553.
• Zabala, A., Pons, X., Díaz-Delgado, R., García, F., Aulí-Llinàs, F., & Serra-Sagristà, J. (2006). Effects of JPEG and JPEG2000 lossy compression on remote sensing image classification for mapping crops and forest areas. In IEEE International Symposium on Geoscience and Remote Sensing (pp. 790-793). doi:10.1109/IGARSS.2006.203.
• Zeng, Y., Zhang, J., Van Genderen, J. L., & Zhang, Y. (2010). Image fusion for land cover change detection. International Journal of Image and Data Fusion, 1(2), 193-215. doi:10.1080/19479831003802832.
• Zhang, C., Franklin, S. E., & Wulder, M. A. (2004). Geostatistical and texture analysis of airborne-acquired images used in forest classification. International Journal of Remote Sensing, 25(4), 859-865. doi:10.1080/01431160310001618059.
• Zhang, D., Wong, A., Indrawan, M., & Lu, G. (2000). Content-based image retrieval using Gabor texture features. IEEE Transactions PAMI, 13-15.