Cellular neural network is adopted for seismic pattern recognition. We design cellular neural network to behave as associative memory according to the stored patterns, and finish the training process of the network. Then we use this associative memory to recognize seismic test patterns. In the experiments, the analyzed seismic patterns are bright spot pattern, right and left pinch-out patterns. From the recognition results, the noisy seismic patterns can be recovered. Seismic pattern recognition can help the analysis and interpretation of seismic data.