Rotation Invariant Automatic Infrared Target Recognition using G-Radon

Abstract

Abstract. In recent research, automatic target recognition (ATR) of infrared targets has been taking a lot of interest to the researchers. A rotation invariant method is useful in target recognition, classification and image analysis to reduce the number of training data. In particular, rotation invariant method, Radon transform, is an effective technique that is used for medical care such as computerized tomography (CT) image. This paper proposes a new rotation invariant algorithm for target recognition. The proposed method combines the gradient information and radon transform. The propose method, called gradient Radon (G-Radon), is applied to synthesized infrared images and compared with traditional radon transform and Zernike moments for validation.