Image super-resolution reconstruction method and system based on edge detection

Abstract

The invention discloses an image super-resolution reconstruction method and system based on edge detection, and the method comprises the steps: taking a high-resolution image as an original image sample, and obtaining a low-resolution image after the image preprocessing; constructing a super-resolution reconstruction network model, and inputting the low-resolution image into the super-resolution reconstruction network model to pre-train the super-resolution reconstruction network model; calculating the super-resolution image and the high-resolution image through a VGG19 network to obtain a perception loss function; carrying out color space conversion and edge extraction on the super-resolution image and the high-resolution image, and obtaining an edge loss function through L1 loss functioncalculation; and combining the perception loss function and the edge loss function in proportion to obtain a loss function Ltotal and update parameters, and inputting the low-resolution image into the trained super-resolution reconstruction network model to obtain a recovered high-resolution image. According to the invention, the defect of fake texture generation is overcome, and the visual effect and authenticity of image restoration are improved.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to an image super-resolution reconstruction method and system based on edge detection. Background technique [0002] With the introduction of convolutional neural networks, deep learning has been widely used in various fields, such as face recognition, target detection, semantic segmentation, pose estimation, etc. But there is no very mature technology in image restoration. Due to motion jitter, physical occlusion or long-distance shooting, the image resolution will be reduced, making it impossible for people to distinguish objects in the image. Therefore, image restoration will also become an indispensable technology for future development. Among them, super-resolution reconstruction is one of the methods to improve image resolution in harsh environments. Its research results can be used in some existing image processing algorithms to improve the recognition and ...

AI Technical Summary

Problems solved by technology

[0004] For the existing super-resolution method for enhancing perceptual quality, using the generative confrontation network can basically achieve a good visual effect. However, the restoration of image texture information also reduces the value of the peak signal-to-noise ratio. This is because the generative confrontation network generates The image is not exactly the same as the original image, and a real pixel is created based on the current pixel, so the generated texture information is not necessarily real

Images