Image Super-Resolution Reconstruction Method based on Improved Cyclic Generative Adversarial Network with Twin Attention Mechanism

The existence of noise components will affect the quality of image super-resolution reconstruction, so an image super-resolution reconstruction method based on improved cyclic generative countermeasure network is proposed. Using the image denoising regularization method, the internal noise of the original image is removed. By introducing the twin attention mechanism into the cyclic generative countermeasure network, an improved cyclic generative countermeasure network is obtained. In the improved cyclic generative countermeasure network, the twin attention model is used to extract the denoised image features, and the super-resolution reconstruction image is generated with the generator. The network discriminator is used to identify whether the reconstructed image is a real image, and the output identification result is a real image to obtain the relevant image super-resolution reconstruction results. Experiments show that this method can effectively denoise the original image and extract image features, and can also reconstruct the image with high quality to improve image resolution and clarity. At different image magnifications, the structural similarity of image reconstruction using this method is high. The subjective opinion score of the image super-resolution reconstruction result of this method is high, with a maximum score of 4.8. The perception index and Frechet inception distance are both small, with values of 21.65 and 14.84, respectively. The image super-resolution reconstruction effect is good.