Image enlargement method based on cubic surfaces with local features as constraints

Abstract The quality of image edges and textures plays a vital role in the visual effect of images. For keeping the features of image edges and textures better, we propose an image enlargement method based on cubic fitting surfaces with local features as constraints. The cubic fitting surface constructed with the edge and the distance as constraints effectively improves the approximation accuracy and shape retention, resulting in sharper edges in the initially enlarged image. The error between the cubic fitting surface and the input image surface leads to the error between the initially enlarged image and the input image. Using image self-similarity to filter the initially enlarged image can further improve its quality. In the iterative optimization process, the cubic surface with higher fitting accuracy is constructed on smaller regions of low resolution error images, which effectively improves the quality of the enlarged image and accelerates the convergence speed. Because the algorithm effectively utilizes the local feature information, compared with other state-of-the-art methods, the new method not only has higher PSNR/SSIM in numerical accuracy, but also has clear edges and textures visually.