{"references": ["C. C. Chen and H. C. Andrews, \"Target-motion-induced radar imaging,\"\nIEEE Trans. Aero. and Electr. Syst., vol. 16, no. 1, pp. 2-14, Jan. 1980.", "D. L. Mensa, High Resolution Radar Cross Section Imaging, Artech\nHouse, Norwood, 1991.", "A. Zyweck and R. E. Bogner, \"High-resolution radar imagery of the\nMirage III aircraft,\" IEEE Trans. Antennas Propag., vol. 42, no. 9, pp.\n1356-1360, 1994.", "S. H. Park, H. T. Kim, K. T. Kim and J. I. Park, \"An efficient range\nalignment algorithm method for long-range ISAR imaging,\" 2009 Int.\nRadar Conf., pp. 1-5, Oct. 2009.", "L. Xi and L. Guosui, J. Ni, \"Autofocusing of ISAR images based on\nentropy minimization,\" IEEE Trans. Aero. and Electr. Syst., vol. 16, no. 1,\npp. 2-14, Jan. 1980.", "S. H. Park, J. H. Jung, H. T. Kim and K. T. Kim, \"Construction of 2D\ntraining database based on high frequency RCS prediction methods,\"\nMicrow. Opt. Techn. Let., vol. 53, no. 1, pp. 223-229, Jan. 2011.", "S. H. Park, K. T. Kim and H.-T. Kim, \"Cross-range scaling algorithm for\nISAR images using 2D Fourier transform and polar mapping\", IEEE\nTrans. on Geosci. Remote Sens., vol. 29, issue 2, pp. 868 - 877, Feb. 2011", "K. T. Kim, D. K. Seo and H. T. Kim, \"Efficient classification of ISAR\nimages,\" IEEE Trans. Antennas Propag., vol. 53, no. 5, pp. 1356-1360,\nMay 1994.", "S. H. Park, K. T. Kim and H. T. Kim, \"Efficient classification of ISAR\nimages using 2D Fourier transform and polar-mapping,\" Korea Inst. Mil.\nSci. Tech. 2012 Annual Conf., pp. 635-638, Jun. 2010."]}

This paper proposes an efficient method to classify inverse synthetic aperture (ISAR) images. Because ISAR images can be translated and rotated in the 2-dimensional image place, invariance to the two factors is indispensable for successful classification. The proposed method achieves invariance to translation and rotation of ISAR images using a combination of two-dimensional Fourier transform, polar mapping and correlation-based alignment of the image. Classification is conducted using a simple matching score classifier. In simulations using the real ISAR images of five scaled models measured in a compact range, the proposed method yields classification ratios higher than 97 %.