Pulse Coupled Neural Network (PCNN) is a new generation artificial neural network (ANN) based on biological vision. It has wide application prospects in the field of digital image processing and artificial intelligence. In this paper, we propose a method to extract face features by studying PCNN theoretical model and its working characteristics. Firstly, the low frequency feature of face image is extracted by wavelet transform. Then, the simplified PCNN is used to extract the corresponding time series of face image reconstructed by wavelet low-frequency coefficient, which is used as the feature sequence of face recognition. Finally, the face recognition process is completed with time series and Euclidean distance. In this paper, we demonstrate the effectiveness of the method with ORL face database.