Abstract: Empirical Mode Decomposition（EMD），a fully data-driven method without using any predetermined filter or wavelet function，is a powerful tool for analyzing composite，nonlinear and non-stationary signals.Based on this，a method is described to address illumination effects in the biometric modality of face recognition using EMD to decompose images into their Intrinsic Mode Function（IMF）.Using these illumination modes the facial image is reconstructed without these illumination distortion components to synthesize a more illumination neutral facial image.Experimental results show that EMD is suitable for feature extraction and the proposed method demonstrates to be feasible for face recognition.