Feature Extraction and Fusion for Automatic Target Recognition Based ISAR Images

This paper presents aircraft target recognition (ATR) system using Inverse Synthetic ApertureRadar (ISAR). The methodology used to design the complete processing chain from the acquisition stepto the recognition (classification) step is based on the artificial intelligence approach. This process isknown as Knowledge Discovery from Data (KDD) which we have adapted to radar target recognitionsystem. We propose a new method for target shape extraction from ISAR images based on the combinationof a modified SUSAN Algorithm and Variational of Level Set. To guarantee the invariance intranslation and rotation of the extracted shape, the moment invariants and Fourier descriptors are used. Inthe second part of this work,We have investigated the impact of the information fusion on our recognitionsystem. Therefore, three combination strategies: probability theory, majority vote and belief theory areapplied at score and decision level. The classification results are obtained using Support VectorMachine (SVM) classifier. In the last section, experimental results are provided and discussed