In this paper, we work on the electromagnetic target recognition problem based on the scattered field measurements. These measurements were obtained both in frequency and time domains by using two 0.8-12 GHz horn antennas in bistatic position and HP8720D vector network analyzer. First, the theory of electromagnetic scattering from a target and singularity expansion method (SEM) are summarized. The importance of complex natural resonance frequencies (CNR) in identification problem is discussed in this part. Afterwards, the results of CNR extraction from the scattered data of three dielectric spheres with different sizes and permitivities are presented by using time-frequency techniques to discriminate these targets from each other. It is also demonstrated that Page distribution produces much better results in this respect as compared to Wigner distribution. © 2005 IEEE.