Compressed sensing (CS) has attracted a lot of attention in recent yea rs,and it remains a hot research topic in pattern recognition and image processing.In this paper,a novel method by integrating compressed sensing with pulse coupled neural networks (PCNN) is put forward for the purpose of over coming the drawback of noise sensitivity and poor time efficiency of the classical PCNN.The proposed method not only has good ability to overcome the noise,but also performs the denoising and image fusion simultaneou sly,whereas denoising and fusion processes are carried out separately for many conventional image fusion a pproaches and this would result in information inconsistency.Nevertheless,by integrating the merits of CS and PCN N,the proposed method can greatly improve the image fusion efficiency and reduce the computation time to s ome extent.Extensive experiments are carried out on the multi-focus images and small-target images. In addition,we detailedly analyze from the respects of fusion performance,noise level,fusion efficiency,algorit hmic stability and so on.And experimental results indicate that the proposed method outperforms some existing image fusion methods in terms of both the visual quality and a variety of quantitative evaluation criteria.