In recent years,convolutional neural networks have been widely used in the field of image super-resolution.The super-resolution algorithm based on co nvolutional neural network has some problems,such as insufficient feature extra ction of image,large number of parameters and difficult training.Therefore,this paper proposes a lightweight image super-resolution reconstruction algorithm based on gated convolutional neural network (GCNN).Firstly,the shallow feature extraction of t he original low-resolution image is carried out by convolution operation.Then, the gated residual blocks (GRB) and long and short residual connections fully extract image feat ures,and its high-efficient structure can also accelerate the network training proce ss.The gated unit (GU) in the GRB uses the regional self-attention mechanism to extract the weight of each feature point in the input feature map. And then it multiplies the gate weight by the input feature element by element a s the output of the GU.Finally,high-resolution images are reconstruct e d using sub-pixel convolution and convolution module.Experiments are conducted on Set14,BSD100,Urban100 and Manga109 datasets.Compared with the classical me thods,not only does the algorithm in this paper have higher peak signal-to-no is e ratio and structural similarity,but also the reconstructed image has clearer contour edges and details.