Image super-resolution reconstruction method, system and related device

Abstract

The invention provides an image super-resolution reconstruction method. The image super-resolution reconstruction method comprises the steps of obtaining a high-resolution image; performing image preprocessing on the high-resolution image to obtain a training set; training the training set by using a multi-scale loss convolutional neural network to obtain a training model; and performing super-resolution reconstruction on a to-be-reconstructed image by using the training module to obtain a super-resolution image. According to the invention, the training model is obtained based on the multi-scale loss convolutional neural network, the loss function in the model is improved, the difference between the SR image and the HR image under different sizes is comprehensively considered, the fusion of high-layer information and low-layer information is realized, and the image super-resolution reconstruction quality is effectively improved. The invention further provides an image super-resolutionreconstruction system, a computer readable storage medium and an image processing terminal, which have the above beneficial effects.

Description

technical field [0001] The present application relates to the field of image processing, in particular to an image super-resolution reconstruction method, system and related devices. Background technique [0002] Image super resolution (super resolution, SR) refers to the process of restoring high resolution (High resolution, HR) images from low resolution (low resolution, LR) images, which is an important aspect of image processing technology in computer vision and image processing. category. It has a wide range of practical applications, such as medical imaging, security monitoring and remote sensing images and other fields. In addition to improving the perceived quality of images, it can also help improve other computer vision tasks. [0003] SR methods can be roughly divided into two categories: traditional methods and deep learning methods. In the past, various classical SR methods have been proposed, including prediction-based methods, edge-based methods, statistica...

AI Technical Summary

Problems solved by technology

However, the current image super-resolution reconstruction does not take into account the differences of images with different resolutions under different sizes, so how to achieve high-quality image super-resolution reconstruction is a technical problem that those skilled in the art need to solve urgently

Images