Image super-resolution reconstruction method based on multi-column convolution neural network

Abstract

The invention discloses an image super-resolution reconstruction method based on a multi-column convolution neural network. Firstly, a multi-column convolution neural network model is designed according to the depth learning algorithm, and includes feature extraction and image reconstruction. Then, the original image is cut into small blocks, and these high-resolution blocks are downsampled to getlow-resolution blocks, and these low-resolution and high-resolution pairs of blocks are used to build the training set. Finally, the model is trained by using the stochastic gradient descent algorithm to get a model that reconstructs the low-resolution image to the high-resolution image, and the input low-resolution image is reconstructed to the corresponding high-resolution image. The method ofthe invention is tested on five universal image databases of Set5, Set14, BSDS100, Urban100 and Manga109, and has high robustness and accuracy.

Description

technical field [0001] The invention relates to an image super-resolution reconstruction method, in particular to a super-resolution reconstruction method based on multi-column convolutional neural network images, which belongs to the utilization of image processing and reconstruction technologies. Background technique [0002] With the development of information technology, images, as the main medium of information dissemination, have been widely used in various scenarios. In many fields, people have high requirements for image quality, so for the rapidly developing information age, it is difficult for low-quality images to meet the needs of specific scenes. Image resolution is an important indicator for measuring image quality. The higher the image resolution, the more detailed information the image contains. Image super-resolution (Super-Resolution, SR) reconstruction belongs to image processing technology, which reconstructs high-resolution (High-Resolution, HR) images ...

AI Technical Summary

Problems solved by technology

[0004] Although the proposed image super-resolution algorithm based on convolutional neural network solves the problems of poor robustness and computational complexity in traditional image super-resolution reconstruction algorithms, the existing image super-resolution algorithm based on convolutional neural network Before extracting the features of the low-resolution image, the low-resolution image must be enlarged to the size of the high-resolution image to be reconstructed by using the Bicubic Interpolation method, and the Extracting features, the image after bicubic interpolation introduces a lot of redundant information, which is not helpful for feature extraction

Therefore, the existing methods still have problems such as poor reconstruction ability and poor visual effect for images with rich details.

Images