This paper presents a novel approach for automatic target recognition (ATR) using inverse synthetic aperture radar (ISAR). This proposed approach is mainly composed of two steps. In the first step, we adopt a statistical method to compute a novel target template from feature de- scriptors. The proposed template is achieved by combining the Gamma statistical parameters of the both dual-tree complex wavelet transform (DT-CWT) coefficients and the scale-invariant feature transform (SIFT) descriptor. In order to validate the proposed target template, we achieve in the second step the recognition task using a sparse representation-based classifica- tion (SRC) method. The performance of the proposed approach has been successfully verified using ISAR images reconstructed from anechoic chamber. The experimental results show that the proposed method can achieve a high average accuracy and is significantly superior to the well-known SVM classifier.