A novel fuzzy jamming recognition approach based on complexity measure of received signal is proposed. The proposed algorithm exploits the LZ complexity and box dimension of received signal as classified characters of jamming pattern. After the mean center and variance of each jamming pattern are calculated by some jamming samples, exponential fuzzy membership function is used to calculate membership value of the recognizing sample. Finally, the jamming pattern of sample is recognized by the maximum membership principle. The simulation results show that the proposed algorithm can recognize common six jamming patterns and QPSK signal accurately.