Pose estimation for ISAR image classification

This paper presents aircraft target recognition (ATR) system using Inverse Synthetic Aperture Radar (ISAR) images. Knowing the pose of the target can improve the ATR performance (recognition rate and computational complexity). So, we propose in this paper a new pose estimator from ISAR images, based on the axis of symmetry and the similarity measure. The method proposed is compared with several approaches proposed recently in the literature, such as 2-D Continuous wavelet Transform and Hough transform. Once the pose of target is estimated, the classification if finally performed by K-Nearest Angle (KNA) classifier which insert the pose information into image retrieval task.